Latent Activation Signature

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Activationsconcept0.800
  Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
• AUPRC Latent Activation Classifiermethod0.785
  Using per-prompt average SAE latent activations and area under precision-recall curve to discriminate aligned from misaligned models
• Activation Additionmethod0.764
  Intervention method that adds a learned direction vector to residual stream activations to steer model behavior
• latent patternsconcept0.743
  Statistical regularities stored in pretrained models.
• Massive Activationsconcept0.741
  Large activation magnitudes in the residual stream that Queipo-de Llano et al. link to causing compression behavior and stages of inference
• Activation Probingconcept0.738
  Technique of reading out model beliefs from internal activations before the final answer token is generated
• Activation Similarityconcept0.737
  Model-independent feature comparison based on correlating activation vectors across a fixed diverse dataset
• Other-Referencing Activationsconcept0.730
  Latent model activations when processing inputs framed from another agent's perspective