ZFancy/awesome-activation-engineering

A curated list of resources for activation engineering

38
/ 100
Emerging

This resource provides a curated collection of research papers and materials focused on "Activation Engineering" for foundation models, particularly Large Language Models (LLMs). It helps AI researchers and developers understand how concepts are represented within these models, how to detect when those concepts are active, and how to influence model behavior by modifying internal activations. The output is a structured list of academic papers and related resources.

132 stars. No commits in the last 6 months.

Use this if you are an AI researcher or developer actively working on understanding, interpreting, or controlling the internal mechanisms of large language models.

Not ideal if you are looking for ready-to-use code, pre-built applications, or a high-level overview of LLMs for non-technical users.

AI-interpretability LLM-research neural-network-analysis model-steering AI-ethics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

132

Forks

8

Language

License

MIT

Last pushed

Oct 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ZFancy/awesome-activation-engineering"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.