hypothesis
active
hypothesis:a-combination-of-crosscoders-and-flexible-decoding-matryoshka-iterative-codebook-could-resolve-the-steering-classification-tension

A combination of crosscoders and flexible decoding (Matryoshka, iterative codebook) could resolve the steering-classification tension

Proposed remedy.

Source paper

extracted_from
Mapping the Latent Space of Llama 3.3 70B - Goodfire
Thomas McGrath

Neighborhood — ranked by edge-count

Frameworks (2)

framework
  • Crosscoders
    supports
    Learn a shared feature space across two models; basis of the work.
  • Nested dictionary approach that inspires the nested loss.

Methods (1)

method

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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