{"total":15,"rows":[{"id":"2505.14352","title":"Towards eliciting latent knowledge from LLMs with mechanistic interpretability","created":"2025-05-20","cited_by_count":19,"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":"2405.17425","title":"From Neurons to Neutrons: A Case Study in Interpretability","created":"2024-05-27","cited_by_count":5,"area":"mechinterp"},{"id":"2510.20479","title":"RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging","created":"2025-10-23","cited_by_count":5,"area":"mechinterp"},{"id":"2606.03002","title":"Perplexity Can Miss SAE Feature Damage Under Quantization","created":"2026-06-02","cited_by_count":5,"area":"mechinterp"},{"id":"2409.10245","title":"From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs","created":"2024-09-16","cited_by_count":3,"area":"mechinterp"},{"id":"2603.00425","title":"Weight Updates as Activation Shifts: A Principled Framework for Steering","created":"2026-02-28","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":"2408.00804","title":"ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model","created":"2024-07-26","cited_by_count":2,"area":"mechinterp"},{"id":"2408.11827","title":"Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models","created":"2024-08-05","cited_by_count":2,"area":"mechinterp"},{"id":"2604.13694","title":"Weight Patching: Toward Source-Level Mechanistic Localization in LLMs","created":"2026-04-15","cited_by_count":2,"area":"mechinterp"},{"id":"2605.28896","title":"Feature Geometry of LoRA Adapters: A Sparse Autoencoder Analysis of Representational Divergence in Fine-Tuned Language Models","created":"2026-05-27","cited_by_count":1,"area":"mechinterp"},{"id":"2608.11025","title":"Data Attribution of Emergent Misalignment with Persona Features","created":"2026-08-11","cited_by_count":1,"area":"mechinterp"},{"id":"2606.06214","title":"Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering","created":"2026-06-04","cited_by_count":0,"area":"mechinterp"},{"id":"2609.06473","title":"Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs","created":"2026-09-06","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}