concept
active
concept:activations-as-an-additional-input-modalityActivations as an additional input modality
Core framing of AOs.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Activation OraclesimplementsFramework training LLMs to answer questions about externally-provided activation vectors
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.
- Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
- Intervention method that adds a learned direction vector to residual stream activations to steer model behavior
- Latent model activations when processing inputs framed from another agent's perspective
- Adding steering vector in forward direction to push model activations toward stronger reflective behavior.
- Method formalized by Rimsky et al. (2024) that this paper adopts for extracting persona vectors
- Mechanism by which activation of an emotion feature sometimes leads to later suppression of that same featurequestion0.764Identified research gap: the paper observes anti-persistence but has no explanation for it
- Large activation magnitudes in the residual stream that Queipo-de Llano et al. link to causing compression behavior and stages of inference
- Add scaled steering vector to layer activations.