A single-layer transformer memorizes random subject-attribute bijections using logarithmic embedding dimension via linear superpositions in embeddings and ReLU-gated selection in the MLP, with zero-shot transfer to new facts and matching multi-hop constructions.
hub Mixed citations
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
Mixed citation behavior. Most common role is background (62%).
86
Pith papers citing it
Background
62% of classified citations
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.
hub tools
citation-role summary
background 7
method 1
citation-polarity summary
claims ledger
- 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 LL
co-cited works
representative citing papers
Function vectors steer LLMs successfully where the logit lens fails to decode the target answer, showing the two properties come apart.
Replay pairing shows LLM agents do not persist plans in hidden states but rely on plans remaining in context, with rapid signal decay and task performance drops when plans are evicted.
Hidden-state convergence at step 4 predicts behavioral consistency in LLM agents on QA tasks (r=-0.35 to -0.83), enabling AUROC 0.97 detection of inconsistent trajectories but not improving accuracy on harder benchmarks.
GEMs track directional trajectories of concepts through transformer layers to extract probes from the post-rotation stable handoff layer, outperforming peak-layer probes in 66.2% of 391 tested cases across 23 models.
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
LLMs encode repeated token counts correctly in residual streams but a format-triggered MLP at 88-93% depth overwrites it with an incorrect fixed value.
PSR models that estimate token-specific steering coefficients from activations outperform standard activation steering and compare favorably to prompting on steering benchmarks.
Large language models encode relational bindings via a cell-based representation: a low-dimensional linear subspace in which each cell corresponds to an entity-relation index pair and attributes are retrieved from the matching cell.
Claude Sonnet 4.5 exhibits functional emotions via abstract internal representations of emotion concepts that causally influence its preferences and misaligned behaviors without implying subjective experience.
NARCBench and five activation-probing methods detect multi-agent collusion with 0.73-1.00 AUROC across distribution shifts and steganographic tasks by aggregating per-agent signals.
Activation probes detect hallucinations pre-generation in large LLMs but cannot correct them via steering, with output confidence outperforming on accuracy.
Refusal in language models is mediated by a single direction in residual stream activations that can be erased to disable safety or added to elicit refusal.
DLMs encode a decodable latent timestep signal in residual activations that can be steered to predictably change model confidence and entropy.
HARC couples harmfulness and refusal directions across prompt and response positions via subspace fine-tuning, achieving better robustness-capability-usability trade-off than six baselines while transferring across model families.
Authority sycophancy in LLMs is a layer-localized erasure of correct answer representations that scales with authority level and resists simple interventions.
Internal probes across three model families fail generalization and specificity tests and therefore do not support robust pre-action misalignment monitoring.
DynaSteer is a dynamic representation editing framework that uses pattern clustering, Fisher-LDA, and lookahead entropy monitoring to steer LLM reasoning trajectories toward truth on MATH and coding tasks.
SHIFT reformulates neuron editing as learnable gate modulation on under 0.01% parameters to let LLMs adaptively balance contextual and parametric knowledge during RAG generation.
A framework is proposed for solving for an AI system's beliefs and desires from its computational facts, with criteria for success tied to interpretability tests and emphasis on holistic attribution.
Across four language models, the linear direction detecting hallucinated entities achieves perfect separability yet lies at cosine 0.12 from the direction that induces refusal, with the gap unchanged by instruction tuning.
Consistency training decodes verifier information from rationale representations but does not produce faithful natural-language explanations.
citing papers explorer
-
Emergent Symbolic Structure in Health Foundation Models: Extraction, Alignment, and Cross-Modal Transfer
Health foundation model embeddings contain an interpretable symbolic organization shared across modalities that supports cross-domain transfer without joint training.
-
Hallucination Detection via Activations of Open-Weight Proxy Analyzers
A framework using activation-based features from small open-weight proxy models detects LLM hallucinations with higher AUC than ReDeEP on RAGTruth, performing consistently across seven analyzer architectures.
-
Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits
Probabilistic circuits detect LLM hallucinations as residual-stream anomalies with up to 99% AUROC and enable dynamic correction that raises truthfulness scores while cutting unnecessary output corruption.
-
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
Probe-geometry alignment erases cross-sequence memorization signatures in LLMs below chance using per-depth rank-one activation interventions with negligible impact on zero-shot capabilities.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Perturbation probing identifies tiny sets of FFN neurons that control refusal templates and language routing in LLMs, enabling precise ablations and directional interventions that alter behavior on benchmarks while preserving safety.
-
Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams
Harmful intent is linearly separable in LLM residual streams across 12 models and multiple architectures, reaching mean AUROC 0.982 while showing protocol-dependent directions and strong generalization to held-out harm benchmarks.
-
LLM Safety From Within: Detecting Harmful Content with Internal Representations
SIREN identifies safety neurons via linear probing on internal LLM layers and combines them with adaptive weighting to detect harm, outperforming prior guard models with 250x fewer parameters.
-
Testing the Limits of Truth Directions in LLMs
Truth directions in LLMs are not universal but depend heavily on model layer, task type and difficulty, and prompt instructions.
-
Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs
Hallucination neurons in LLMs are domain-specific, with cross-domain classifiers dropping from AUROC 0.783 within-domain to 0.563 across domains.
-
Emergent Manifold Separability during Reasoning in Large Language Models
Reasoning in LLMs produces a transient geometric pulse in which concept manifolds untangle into linearly separable subspaces immediately before computation and compress afterward.
-
Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis
A new framework using Task Subspace Logit Attribution localizes attention heads specialized for task recognition and task learning in in-context learning, showing they align and rotate hidden states within a task subspace.
-
Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment
Disentangled Safety Adapters decouple safety computations from task-optimized LLMs via lightweight adapters, yielding up to 53% better AUC on safety tasks and dynamic inference-time alignment with reduced performance trade-offs.
-
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
SEPs approximate semantic entropy from single-generation hidden states to enable cheap and robust hallucination detection in LLMs.
-
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
A factorized study finds raw hidden states and attention features hard to beat in-domain for LLM uncertainty probes, but structured compressed features are more robust under distribution shift, with pretrained probes transferring to open-ended generation.
-
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
A new pipeline uses interpretability to characterize concepts in preference data and shape rewards via feature or data interventions during LM post-training.
-
Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
Activation steering with Gram-Schmidt orthogonalization enables disentangled, deterministic control of pitch and duration attributes in the Multitrack Music Transformer without retraining.
-
UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering
UniSteer trains a conditional flow matching model on LLM residual-stream activations to enable text-conditioned steering and classification across multiple behavioral tasks.
-
Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
Palette identifies refusal directions via multi-objective search, internalizes them through lightweight adaptation, and supports on-demand multi-domain authorization via independent learning and parameter merging.
-
Relational Linear Properties in Language Models: An Empirical Investigation
Introduces KL-divergence probing to test relational linearity and reports its variation across models, layers, and paraphrased queries on four datasets.
-
Multi-Turn Neural Transparency: Surfacing Neural Activations Improves User Calibration to LLM Behavioral Drift
Multi-turn neural transparency using behavioral vectors and dynamic visualizations improves user anticipation and evaluation of LLM trait expression while reducing overconfidence, per a randomized study with 246 participants.
-
Temporal Preference Concepts and their Functions in a Large Language Model
Causal localization via attribution and patching identifies a temporal preference subgraph in mid-to-upper layers of Qwen3-4B-Instruct-2507, with time-horizon geometry in the residual stream and initial evidence for steering-vector control.
-
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
HyperLens reveals that deeper transformer layers magnify small confidence changes into fine-grained trajectories, allowing quantification of cognitive effort where complex tasks demand more and standard SFT can reduce it.
-
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
-
Negative Before Positive: Asymmetric Valence Processing in Large Language Models
Negative valence localizes to early layers and positive valence to mid-to-late layers in LLMs, with the directions being causally steerable.
-
Exploring Concreteness Through a Figurative Lens
LLMs compress concreteness into a consistent 1D direction in mid-to-late layers that separates literal from figurative noun uses and supports efficient classification plus steering.
-
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
SIVR detects LLM hallucinations by learning from token-wise and layer-wise variance patterns in internal hidden states, outperforming baselines with better generalization and less training data.
-
H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models
H-probes locate low-dimensional subspaces encoding hierarchy in LLM activations for synthetic tree tasks, show causal importance and generalization, and detect weaker signals in mathematical reasoning traces.
-
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.
-
Risk Reporting for Developers' Internal AI Model Use
A harmonized risk reporting standard for internal frontier AI model use, structured around autonomous misbehavior and insider threats using means, motive, and opportunity factors.
-
Mechanistic Interpretability Needs Philosophy
The paper claims that mechanistic interpretability needs philosophy as a partner to clarify concepts, refine methods, and navigate epistemic and ethical complexities in AI systems.
- Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models
- The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior
- From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents
- Prompt Injection as Role Confusion
- Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought