method
active
method:autosteerAutoSteer
Functionality that automatically finds SAE latents for a desired behaviour and sets their weights.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Modifying model behavior by clamping SAE feature activations to specific values during forward pass.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Neural network architecture that learns compressed representations; SOHMs are functionally equivalent.
- Automated benchmarking framework for evaluating LLM meta-cognition, mentioned as related work.
- Mechanism of self-sustaining organization in nonequilibrium systems; relevant to understanding intention formation.
- Foundational computational paradigm of local rules producing emergent global behavior, extended by this work
- Activation-triggered examples plus direct logit attribution.
- Baseline persistence of any probe direction arising from the autoregressive nature of LLMs, not specific to emotion content