Activation inversion metamodels scale interpretation of residual stream directions
MAEMs generate text exemplars that activate supplied residual stream directions better than corpus search or autoencoders.
Stories per day · 30 days
5 stories, newest first · one card per story
Stories tagged #residual-stream
Lexical reference frames read LM hidden states without a lens
LexFrame[1] reaches 0.97 coherence on SmolLM3-3B and OLMo3-7B, versus 0.30 and 0.35 for fixed lenses.
U-Space: Uncovering When and Why Uncertainty Arises in Language Models
U-Space maps language-model residual states into a subspace that tracks token-level doubt and certainty without extra training.
The Geometry of Inference in Transformer Residual Streams
Six language models show residual streams become geometrically specific to their own final states during inference.
Your Model Is Leaking: Covert Information Transfer through LLM Residual Streams
A residual-stream covert-channel attack hides sensitive information in LLM intermediate activations, recoverable with a simple linear decoder without retraining or weight modification.
1