claim
active
claim:llama-3-3-70b-is-to-the-authors-knowledge-the-most-capable-openly-available-model-with-interpretability-toolingLlama 3.3 70B is, to the authors' knowledge, the most capable openly available model with interpretability tooling
Positioning claim of the release.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Motivation for the release.
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.
- Model-specific difference in persona susceptibility
- Llama-3.3-70B exhibits internal consistency-checking mechanisms that operate during inferenceclaim0.818Central interpretive claim of the paper supported by causal ablation and activation evidence
- One of four LLMs selected; larger model with D=8192 embedding dimension; analyzed across proportionally aligned layers.
- Replication across open-weight models supports scale-emergence finding
- Scale test.
- App. E.
- The model used in Experiment 2 for SAE feature steering experiments via Goodfire API
- One of four LLMs selected for representation analysis; embedding dimension D=4096; used as demonstration model in scatter plots.