{"total":19,"rows":[{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2502.14258","title":"Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information","created":"2025-02-20","cited_by_count":15,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2605.01844","title":"The Cylindrical Representation Hypothesis for Language Model Steering","created":"2026-05-03","cited_by_count":5,"area":null},{"id":"2602.02224","title":"Spectral Superposition: A Theory of Feature Geometry","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2510.08734","title":"Transmuting prompts into weights","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2604.10158","title":"Tracing the Thought of a Grandmaster-level Chess-Playing Transformer","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2605.12813","title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.02528","title":"Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2607.20778","title":"Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2602.01716","title":"Mechanistic Indicators of Steering Effectiveness in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2605.28669","title":"Sense Representations Are Inducible Interfaces","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.13425","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.10142","title":"Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.38718","title":"MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.17713","title":"Confine to the Task, Anchor the Rest: Concept-Guided Retention Regularizer for Parameter-Efficient Fine-Tuning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}