Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

IBM/activation-steering

[ICLR 2025] General-purpose activation steering library

Owner
IBM (organization)
Stars
Stars: 196
Forks
Forks: 29
Language
Python
License
Apache-2.0
Created
2024
Topics
refusalsteeringactivation-steeringllm-steeringalignmentrepresentation-engineering
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by IBM

All 172 repos by IBM

Nearby in Python

All Python repos