AI interpretability researcher. Building Lilly: self-steering cognitive AI with SAEs, TransformerLens, 8D Plutchik affect steering & Active Inference.
- Tacoma, WA
- https://rmulligan.github.io
Highlights
- Pro
Pinned Loading
-
lilly-steering
lilly-steering PublicAffect-driven activation steering for LLMs: 8D Plutchik emotional field, Evalatis evolutionary steering, memory-driven resonator
Python
-
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.




