Papers2

All Beginner Intermediate Advanced

All Sources arXiv

#feed-forward networks

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Intermediate

Hengyuan Zhang, Zhihao Zhang et al.Jan 20arXiv

This survey turns model understanding into a step-by-step repair toolkit called Locate, Steer, and Improve.

#mechanistic interpretability#residual stream#attention heads

The AI Hippocampus: How Far are We From Human Memory?

Intermediate

Zixia Jia, Jiaqi Li et al.Jan 14arXiv

This survey asks how close AI memory systems are to human memory and organizes the answer into three parts: implicit memory (inside the model), explicit memory (outside storage you can look up), and agentic memory (what an AI agent keeps over time to plan and act).

#LLM memory#implicit memory#explicit memory