{"total":33,"rows":[{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2411.14257","title":"Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models","created":"2024-11-21","cited_by_count":115,"area":"mechinterp"},{"id":"2312.17249","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","created":"2023-12-28","cited_by_count":67,"area":"mechinterp"},{"id":"2509.10625","title":"No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes","created":"2025-09-12","cited_by_count":38,"area":"mechinterp"},{"id":"2311.15131","title":"Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching","created":"2023-11-25","cited_by_count":24,"area":"mechinterp"},{"id":"2503.05371","title":"Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs","created":"2025-03-07","cited_by_count":14,"area":"mechinterp"},{"id":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","cited_by_count":13,"area":"mechinterp"},{"id":"2404.13752","title":"Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models","created":"2024-04-21","cited_by_count":12,"area":"mechinterp"},{"id":"2602.01425","title":"One Probe Won't Catch Them All: Towards Targeted Deception Detection","created":"2026-02-01","cited_by_count":9,"area":"mechinterp"},{"id":"2603.25052","title":"Closing the Confidence-Faithfulness Gap in Large Language Models","created":"2026-03-26","cited_by_count":8,"area":"mechinterp"},{"id":"2509.03518","title":"Can LLMs Lie? Investigation beyond Hallucination","created":"2025-09-03","cited_by_count":7,"area":"mechinterp"},{"id":"2506.18852","title":"Mechanistic Interpretability Needs Philosophy","created":"2025-06-23","cited_by_count":6,"area":"mechinterp"},{"id":"2604.19974","title":"Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders","created":"2026-04-21","cited_by_count":6,"area":"mechinterp"},{"id":"2607.07003","title":"Dissociating the Internal Representations of Sycophancy in LLMs","created":"2026-07-08","cited_by_count":6,"area":"mechinterp"},{"id":"2604.16430","title":"HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders","created":"2026-04-06","cited_by_count":5,"area":"mechinterp"},{"id":"2505.06262","title":"Dialz: A Python Toolkit for Steering Vectors","created":"2025-05-04","cited_by_count":4,"area":"mechinterp"},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"area":"mechinterp"},{"id":"2505.17760","title":"But what is your honest answer? Aiding LLM-judges with honest alternatives using steering vectors","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2606.02628","title":"Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs","created":"2026-05-30","cited_by_count":3,"area":"mechinterp"},{"id":"2604.13068","title":"Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing","created":"2026-03-20","cited_by_count":2,"area":"mechinterp"},{"id":"2608.08024","title":"Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States","created":"2026-08-08","cited_by_count":2,"area":"mechinterp"},{"id":"2312.03140","title":"FlexModel: A Framework for Interpretability of Distributed Large Language Models","created":"2023-12-05","cited_by_count":1,"area":"mechinterp"},{"id":"2505.16526","title":"EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance","created":"2025-05-22","cited_by_count":1,"area":"mechinterp"},{"id":"2601.22818","title":"Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"mechinterp"},{"id":"2603.13259","title":"How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint Processing","created":"2026-02-25","cited_by_count":1,"area":"mechinterp"},{"id":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2606.26523","title":"Radical AI Interpretability","created":"2026-06-25","cited_by_count":1,"area":"mechinterp"},{"id":"2605.09391","title":"Do Linear Probes Generalize Better in Persona Coordinates?","created":"2026-05-10","cited_by_count":0,"area":"mechinterp"},{"id":"2608.07208","title":"Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes","created":"2026-08-07","cited_by_count":0,"area":"mechinterp"},{"id":"2609.01361","title":"Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA","created":"2026-09-01","cited_by_count":0,"area":"mechinterp"},{"id":"2609.24821","title":"The Answer-Basin Representation Hypothesis: We Are Not Probing or Steering Concepts","created":"2026-09-21","cited_by_count":0,"area":"mechinterp"},{"id":"2609.32964","title":"The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining","created":"2026-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2609.36813","title":"RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}