The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

TL;DR

This study demonstrates that large language models (LLMs) linearly encode truth/falsehood in their internal representations, validated through transfer and causal intervention experiments, especially at scale.

cs.AI 🔴 Advanced 2023-10-11 677 citations 63 views
Samuel Marks Max Tegmark
Natural Language Processing Model Interpretability Linear Representation Causal Inference Model Scaling

Key Findings

Methodology

This work employs curated high-quality datasets of simple true/false statements, combining principal component analysis (PCA) visualizations, transfer learning experiments, and causal interventions. Probes trained on one dataset are tested for generalization across different datasets, assessing the universality of the truth representation. Residual stream activations are patched to localize causally relevant hidden states, and linear directions are manipulated to observe causal effects on model outputs. The core focus is on whether models develop an abstract ‘truth’ space that generalizes across diverse inputs and scales.

Key Results

  • In LLaMA-2-70B, the true/false representations form a clear linear separation in PCA space, with larger models showing more abstract and generalizable truth encodings. Transfer experiments reveal that probes trained on one dataset achieve over 95% accuracy when applied to structurally different datasets, indicating a shared linear truth space.
  • Causal intervention experiments demonstrate that shifting the hidden states along identified linear directions can flip the model’s judgment of statements, e.g., turning false statements into true ones and vice versa. These directions are localized to a small set of hidden states, especially in the final layers, which encode the model’s explicit truth/falsehood prediction.
  • Simple difference-in-means probes outperform more complex methods in causal relevance, providing a robust, interpretable way to identify the directions most causally implicated in the model’s outputs. These findings suggest that the internal ‘truth’ space is not only linearly represented but also causally operative.

Significance

This research addresses a fundamental question in AI interpretability: do large language models internally represent factual truth in a structured, manipulable way? The evidence that truth is linearly encoded and causally accessible at scale advances our understanding of how models store and utilize knowledge. It provides a pathway for developing more transparent, trustworthy AI systems by enabling targeted interventions and explanations. Moreover, the methodology bridges the gap between statistical correlation and causal inference, offering a new toolkit for model interpretability. These insights are crucial for deploying AI in high-stakes environments where understanding the basis of decisions is essential.

Technical Contribution

The paper introduces a comprehensive framework combining high-quality datasets, PCA visualization, transferability tests, and causal interventions to analyze internal representations. The key technical innovation is the use of simple difference-in-means probes, which are computationally efficient and causally more relevant than traditional logistic regression probes. The study also systematically examines the evolution of truth representations across model scales, revealing a hierarchical development from surface features to abstract concepts. These contributions provide new theoretical and practical tools for interpretability research, emphasizing causal operability of internal spaces.

Novelty

This work is the first to rigorously demonstrate that large-scale LLMs develop a linear, causally relevant ‘truth’ space that generalizes across diverse datasets and is manipulable via targeted interventions. Unlike prior studies that relied solely on correlation-based probes, this research employs causal experiments to validate the functional importance of identified directions. The integration of transfer learning, visualization, and causal manipulation offers a holistic view of internal knowledge representation, setting a new standard in interpretability and causal analysis of neural models.

Limitations

  • The datasets used are limited to simple, unambiguous factual statements; the approach’s effectiveness on complex, multi-hop reasoning or ambiguous statements remains untested. This limits the scope of the current findings to straightforward factual knowledge.
  • Causal interventions focus on linear directions in residual stream activations, which may oversimplify the potentially distributed or nonlinear nature of internal representations, leaving open the question of how these findings extend to more complex or entangled representations.
  • While large models show strong linear truth encoding, smaller models or models trained on different architectures may not exhibit the same properties, indicating a potential scale-dependence and architecture-specific effect that warrants further investigation.

Future Work

Future research will explore the generalization of linear truth spaces to more complex reasoning tasks, multi-modal data, and real-world scenarios. Developing methods to identify and manipulate nonlinear or distributed representations of truth will be crucial. Additionally, integrating these insights into model training and fine-tuning processes could improve factual accuracy and robustness. Extending causal analysis to other internal components and understanding the developmental trajectory of truth representations across training stages are promising directions. The ultimate goal is to build models with transparent, causally grounded internal knowledge structures that can be reliably controlled and interpreted.

AI Executive Summary

In the rapidly advancing field of artificial intelligence, understanding how large language models (LLMs) internally represent knowledge remains a central challenge. Despite their impressive performance across various NLP tasks, these models often produce false or misleading outputs, raising concerns about their reliability and interpretability. Existing interpretability methods, such as probing internal activations with logistic regression, have yielded mixed results, with questions about their generalization and causal relevance.

This study by Samuel Marks and Max Tegmark addresses this gap by systematically investigating whether LLMs develop an internal, linear representation of factual truth. Using high-quality datasets of simple true/false statements, the authors employ a multi-pronged approach: visualizing internal representations with PCA, testing transferability of probes trained on one dataset to others, and performing causal interventions by manipulating hidden states. Their findings reveal that, at sufficient scale, LLMs encode truth and falsehood in a linearly separable space, which generalizes across diverse datasets and is causally implicated in the model’s outputs.

The core technical innovation is the use of a simple, yet powerful, difference-in-means probe that identifies directions in the internal space most causally related to the model’s judgments. These directions, localized to a small set of hidden states, can be manipulated to flip the model’s output, providing strong causal evidence for the internal encoding of truth. The experiments demonstrate that larger models, such as LLaMA-2-70B, exhibit more abstract and generalizable truth representations, highlighting the role of scale in emergent capabilities.

Beyond technical insights, this work has profound implications for AI safety, transparency, and trustworthiness. It suggests that models do not merely memorize facts but develop structured, manipulable internal spaces for factual knowledge. This opens avenues for targeted interpretability, bias mitigation, and robust knowledge editing. However, the study also acknowledges limitations: the focus on simple factual statements, the linearity assumption, and the need to extend findings to more complex reasoning.

Looking ahead, future work will explore how these linear truth spaces evolve during training, how they can be extended to multi-hop reasoning, and how to leverage them for building more transparent AI systems. Overall, this research marks a significant step toward demystifying the internal mechanics of large language models, paving the way for more trustworthy and controllable AI technologies.

Deep Dive

Abstract

Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM's internal activations. However, this line of work is controversial, with some authors pointing out failures of these probes to generalize in basic ways, among other conceptual issues. In this work, we use high-quality datasets of simple true/false statements to study in detail the structure of LLM representations of truth, drawing on three lines of evidence: 1. Visualizations of LLM true/false statement representations, which reveal clear linear structure. 2. Transfer experiments in which probes trained on one dataset generalize to different datasets. 3. Causal evidence obtained by surgically intervening in a LLM's forward pass, causing it to treat false statements as true and vice versa. Overall, we present evidence that at sufficient scale, LLMs linearly represent the truth or falsehood of factual statements. We also show that simple difference-in-mean probes generalize as well as other probing techniques while identifying directions which are more causally implicated in model outputs.

cs.AI

References (20)

LLaMA: Open and Efficient Foundation Language Models

Hugo Touvron, Thibaut Lavril, Gautier Izacard et al.

2023 21315 citations ⭐ Influential View Analysis →

Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models

Matthew Finlayson, Aaron Mueller, Stuart M. Shieber et al.

2021 154 citations ⭐ Influential View Analysis →

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Kenneth Li, Aspen K. Hopkins, David Bau et al.

2022 525 citations ⭐ Influential View Analysis →

Discovering Latent Knowledge in Language Models Without Supervision

Collin Burns, Haotian Ye, D. Klein et al.

2022 829 citations ⭐ Influential View Analysis →

The Internal State of an LLM Knows When its Lying

A. Azaria, Tom M. Mitchell

2023 762 citations ⭐ Influential View Analysis →

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Kenneth Li, Oam Patel, Fernanda B. Viégas et al.

2023 1383 citations ⭐ Influential View Analysis →

Still no lie detector for language models: probing empirical and conceptual roadblocks

B. A. Levinstein, Daniel A. Herrmann

2023 109 citations ⭐ Influential View Analysis →

Explore, Establish, Exploit: Red Teaming Language Models from Scratch

Stephen Casper, Jason Lin, Joe Kwon et al.

2023 141 citations ⭐ Influential View Analysis →

What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models

Fahim Dalvi, Nadir Durrani, Hassan Sajjad et al.

2018 226 citations View Analysis →

What Is Data Science

Longbing Cao

2018 571 citations

Implicit Representations of Meaning in Neural Language Models

Belinda Z. Li, Maxwell Nye, Jacob Andreas

2021 246 citations View Analysis →

Multimodal Neurons in Artificial Neural Networks

Gabriel Goh, Nick Cammarata, Chelsea Voss et al.

2021 420 citations

Probing Classifiers: Promises, Shortcomings, and Advances

Yonatan Belinkov

2021 983 citations View Analysis →

Understanding the role of individual units in a deep neural network

David Bau, Jun-Yan Zhu, Hendrik Strobelt et al.

2020 542 citations View Analysis →

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

Atticus Geiger, Kyle Richardson, Christopher Potts

2020 135 citations

Designing and Interpreting Probes with Control Tasks

John Hewitt, Percy Liang

2019 804 citations View Analysis →

Investigating Gender Bias in Language Models Using Causal Mediation Analysis

Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov et al.

2020 776 citations

Mapping Language Models to Grounded Conceptual Spaces

Roma Patel, Ellie Pavlick

2022 211 citations

The Implicit Bias of Gradient Descent on Separable Data

Daniel Soudry, Elad Hoffer, Suriya Gunasekar et al.

2017 1156 citations View Analysis →

TruthfulQA: Measuring How Models Mimic Human Falsehoods

Stephanie C. Lin, Jacob Hilton, Owain Evans

2021 3797 citations View Analysis →

Cited By (20)

Linear representations of grammaticality in neural language models

2026 ⭐ Influential View Analysis →

Language Models Encode the Contextual Truth of Propositions

2026 ⭐ Influential View Analysis →

On the Robustness of LLMs'Internal Representation of Code Correctness

2026 ⭐ Influential View Analysis →

STEREODISCO: Discovering Stereotypicality in LLMs

2026 ⭐ Influential View Analysis →

Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates

The Refusal Residue: When Probes Catch Alignment Faking and When They Don't

Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control

2026 1 citations View Analysis →

How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?

The Anatomy of a Truth Direction: Knowledge-Dependent Dimensionality, a Relational Law, and a Convergent Category Geometry in Small Language Models

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary

Diagnosing Correctness Probes under Self-Judgement Confounding

Peirce's revenge on the Chinese Room

2026

Misalignment Has a Personality: A Big Five Account of Emergent Misalignment

Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models

Cloud-ScPO: Hidden-State Geometry for Semi-Supervised Preference Optimization in LLM Reasoning

Probing the 3D Object-Level Understanding of Pre-Trained Detection Transformers

Semantic Alignment of AI Models: Concept Collapse, Checkpoint Dynamics, and Cross-Lingual Transfer

Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs

When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives

Test, then Route: How Language Models Execute In-Context Conditional Rules Across Models and Languages