activation-steering repositories
Trending repositories tagged activation-steering, ranked by trending score. Updated daily.
-
1
ShutongLiang/Neural-State-OS
Calibrated internal-state modulation, readout, and neural observability for local dense language models.
GitHub · Python · 293 stars · 0 forks · +88 stars in 24 hours · Trending score 2.11
-
2
SajjadPSavoji/awesome-weight-space-programming
A curated list of weight-space programming: LLMs that read, edit and write the weights of other neural networks directly. Updated daily.
GitHub · Python · 9 stars · 3 forks · +4 stars in 24 hours · Trending score 0.85
-
3
moudrkat/steeropathy
Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions.
GitHub · Python · 29 stars · 3 forks · 0 stars in 24 hours · Trending score 0.28
-
4
wisent-ai/ster
GitHub · Rust · 346 stars · 33 forks · 0 stars in 24 hours · Trending score 0.05
-
5
moudrkat/brainscope
OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope
GitHub · Python · 56 stars · 11 forks · 0 stars in 24 hours · Trending score 0.05
-
6
EigenformAI/modulo
Modulo lets agents running local models try modifying their own activations to change their inner state. Changes decay after a certain time and can be undone at any time.
GitHub · Python · 42 stars · 0 forks · 0 stars in 24 hours · Trending score 0.04
-
7
ant-research/Awesome-Refusal-Suppression
A bilingual awesome list for refusal suppression research: benchmarks, papers, tools, models, and ecosystem updates.
GitHub · 15 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
8
yulinlp/How-LLMs-Use-Memory
Public code repo for "How Do Language Models Use Memory? From Internal Strategy Readout to Adaptive Control" (ICLR 2027, Under Review).
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00