{"total":14,"rows":[{"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":"2410.12299","title":"Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors","created":"2024-10-16","cited_by_count":63,"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":"2508.17621","title":"Steering When Necessary: Flexible Steering Large Language Models with Backtracking","created":"2025-08-25","cited_by_count":8,"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":"2405.15756","title":"Wasserstein Distances, Neuronal Entanglement, and Sparsity","created":"2024-05-24","cited_by_count":6,"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":"2410.06225","title":"A Timeline and Analysis for Representation Plasticity in Large Language Models","created":"2024-10-08","cited_by_count":0,"area":"mechinterp"},{"id":"2506.20083","title":"Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder","created":"2025-06-25","cited_by_count":0,"area":"mechinterp"},{"id":"2608.08383","title":"Safety Cost of Steering Vectors Is Separable and Reducible","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2608.27510","title":"How Do Linear Probes Emerge? A Circuit-Tracing Framework with Concept-Targeted Attribution","created":"2026-08-27","cited_by_count":0,"area":"mechinterp"},{"id":"2610.05794","title":"A Testable Theory of Atomic Features","created":"2026-10-05","cited_by_count":0,"area":"mechinterp"},{"id":"2610.19827","title":"MAPLE: A Multi-Axis Parametric Knowledge Extraction Lens for LLM Evaluation","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}