{"total":70,"rows":[{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2503.03730","title":"Towards Understanding Distilled Reasoning Models: A Representational Approach","created":"2025-03-05","cited_by_count":26,"area":"lr"},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2507.12379","title":"Probing for Arithmetic Errors in Language Models","created":"2025-07-16","cited_by_count":18,"area":null},{"id":"2502.19981","title":"The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs","created":"2025-02-27","cited_by_count":15,"area":null},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2602.11246","title":"How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?","created":"2026-02-11","cited_by_count":12,"area":null},{"id":"2603.09313","title":"Curveball Steering: The Right Direction To Steer Isn't Always Linear","created":"2026-03-10","cited_by_count":11,"area":"mechinterp"},{"id":"2602.03655","title":"Sequential Group Composition: A Window into the Mechanics of Deep Learning","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2511.08379","title":"SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models","created":"2025-11-11","cited_by_count":9,"area":"alignment"},{"id":"2505.05145","title":"Understanding In-context Learning of Addition via Activation Subspaces","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2510.00184","title":"Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2510.26784","title":"LLMs Process Lists With General Filter Heads","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2602.02385","title":"Transformers learn factored representations","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2502.10871","title":"Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs","created":"2025-02-15","cited_by_count":6,"area":null},{"id":"2508.02513","title":"Modular Arithmetic: Language Models Solve Math Digit by Digit","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2603.15121","title":"Establishing Construct Validity in LLM Capability Benchmarks Requires Nomological Networks","created":"2026-03-16","cited_by_count":6,"area":null},{"id":"2604.20817","title":"Convergent Evolution: How Different Language Models Learn Similar Number Representations","created":"2026-04-22","cited_by_count":6,"area":null},{"id":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2506.06607","title":"Training-Free Tokenizer Transplantation via Orthogonal Matching Pursuit","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2506.07824","title":"Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2506.08966","title":"Pre-trained Language Models Learn Remarkably Accurate Representations of Numbers","created":"2025-06-10","cited_by_count":4,"area":null},{"id":"2510.08009","title":"Language Models Do Not Embed Numbers Continuously","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2602.02224","title":"Spectral Superposition: A Theory of Feature Geometry","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2506.16975","title":"Latent Concept Disentanglement in Transformer-based Language Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2606.03330","title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2505.12268","title":"$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks","created":"2025-05-18","cited_by_count":2,"area":"mechinterp"},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2510.26285","title":"Language Models Learn Universal Representations of Numbers and Here's Why You Should Care","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2604.02685","title":"Finding Belief Geometries with Sparse Autoencoders","created":"2026-04-03","cited_by_count":2,"area":"mechinterp"},{"id":"2606.09607","title":"Closure-Validated Circuit Discovery in Attention Heads: Co-activation Proposes, Ablation Disposes","created":"2026-06-08","cited_by_count":2,"area":"mechinterp"},{"id":"2606.29522","title":"When Does Activation Steering Change What a Model Computes From?","created":"2026-06-28","cited_by_count":2,"area":"mechinterp"},{"id":"2511.13371","title":"Cognitive Maps in Language Models: A Mechanistic Analysis of Spatial Planning","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2601.04260","title":"Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models","created":"2026-01-07","cited_by_count":1,"area":"lr"},{"id":"2602.10416","title":"AI-rithmetic","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.13524","title":"Singular Vectors of Attention Heads Align with Features","created":"2026-02-13","cited_by_count":1,"area":"mechinterp"},{"id":"2605.09967","title":"Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions","created":"2026-05-11","cited_by_count":1,"area":"mechinterp"},{"id":"2605.21706","title":"Latent-space Attacks for Refusal Evasion in Language Models","created":"2026-05-20","cited_by_count":1,"area":"alignment"},{"id":"2605.24942","title":"Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2605.29126","title":"When and How Long? The Readout-Mediator Angle in Temporal Reasoning","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.24026","title":"Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2607.16693","title":"Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs","created":"2026-07-18","cited_by_count":1,"area":"mechinterp"},{"id":"2609.07183","title":"CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2503.00224","title":"\\`A la recherche du sens perdu: your favourite LLM might have more to say than you can understand","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2509.23143","title":"MathBode: Measuring the Stability of LLM Reasoning using Frequency Response","created":"2025-09-27","cited_by_count":0,"area":"lr"},{"id":"2511.04053","title":"Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models","created":"2025-11-06","cited_by_count":0,"area":"lr"},{"id":"2605.00847","title":"H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.14749","title":"Non-linear Interventions on Large Language Models","created":"2026-05-14","cited_by_count":0,"area":"mechinterp"},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.03982","title":"Language Models Compare Quantities Using Number-specific and Unit-specific Heuristics","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.05194","title":"Temporal Preference Concepts and their Functions in a Large Language Model","created":"2026-05-11","cited_by_count":0,"area":"mechinterp"},{"id":"2606.17037","title":"The Importance of Phase in Neural Representations: An Internal Oppenheim-Lim Test of Image Classifiers","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.11197","title":"Beyond a Bag of Features: Set-Level Instability in Sparse Autoencoders","created":"2026-08-11","cited_by_count":0,"area":"mechinterp"},{"id":"2609.09556","title":"High-probability guarantees for linear accessibility in feature superposition","created":"2026-09-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.13072","title":"MAxBench: A Multinomial Concept Recovery Benchmark","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35970","title":"Causal and Interpretable Structures in LLM Compositional Tasks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36079","title":"A Polyphonic Conception of AI Understanding","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37680","title":"When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.38958","title":"Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}