Search papers, labs, and topics across Lattice.
3
3
4
6
LLMs often know the answer long before their "reasoning" suggests, wasting tokens on performative chain-of-thought.
Precisely steer LLM behaviors like refusal, sycophancy, and style transfer by surgically activating just a few key attention heads identified via Generative Causal Mediation.
Forget sparse autoencoders: semi-nonnegative matrix factorization directly dissects MLP activations into human-interpretable features that causally steer LLMs better.
