STA selects sparse autoencoder features by activation amplitude and frequency to build steering vectors that improve LLM safety control over prompt engineering and standard steering.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
STA selects sparse autoencoder features by activation amplitude and frequency to build steering vectors that improve LLM safety control over prompt engineering and standard steering.