all tags

interpretability

19 notes carry this tag — 1 moc, 8 claims, 1 observation, 2 questions, 4 captures, 3 essays. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

Essays

• 
  a better story
  essay drafting 2026-08-02 · interpretability, chain-of-thought, hallucination, jailbreak, attribution-graphs
• 
  what the model says it did
  essay draft 2026-07-07 · introspection, chain-of-thought, interpretability, rationality, discontinuous-agents
• 
  What the model says it did
  essay draft 2026-05-26 · introspection, chain-of-thought, interpretability, rationality, discontinuous-agents

Everything else

• The 'same output via opposite mechanisms' shape recurs from the ELIZA/PARRY pairing to coexisting pathways inside one LLM — but not in the vault's model-collapse corpus, which carries a different shape
  observation seedling Tier 1 2026-09-12 · imitation-game, eliza, parry, interpretability, mechanism
• Does 'same surface behavior via opposite mechanisms' recur in the vault's model-collapse or imitation-game material?
  capture promoted Tier 1 2026-09-09 · imitation-game, turing-test, eliza, parry, model-collapse
• The account and the act — what attribution-graph interpretability found inside Claude, and where the traced mechanism overturns the legible story
  topic map 2026-08-01 · interpretability, attribution-graphs, mechanistic-interpretability, chain-of-thought, anthropic
• Does Anthropic's biology-of-an-LLM report state that steering the planned rhyme word changed the completion in ~70% of resamples?
  capture promoted Tier 1 2026-07-25 · anthropic, interpretability, mechanistic-interpretability, claude-3.5-haiku, poetry-planning
• Steering Claude's rhyme-plan feature swaps the target rhyme word under ablation, or abandons rhyme entirely under concept injection
  claim seedling Tier 1 2026-07-25 · interpretability, anthropic, attribution-graphs, mechanism, planning
• Capture: Does Anthropic's "On the Biology of a Large Language Model" say refusal circuitry activates primarily at sentence boundaries?
  capture promoted Tier 1 2026-07-24 · anthropic, interpretability, mechanistic-interpretability, circuit-tracing, refusal
• In the BOMB jailbreak, sentence-boundary features delay an already-triggered refusal rather than cause it, and the paper flags the mechanism as not fully traced
  claim seedling Tier 1 2026-07-24 · interpretability, anthropic, attribution-graphs, mechanism, refusal
• Anthropic's biology-of-an-LLM report frames general refusal as a harmful-request-recognition feature chain, not sentence-structure detection
  claim seedling Tier 1 2026-07-24 · interpretability, anthropic, attribution-graphs, mechanism, refusal
• Four attribution-graph 'chains' in Anthropic's biology-of-an-LLM report, and which one reads most like genuine reasoning
  capture promoted Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Claude performs genuine two-step internal reasoning on 'the capital of the state containing Dallas' (Dallas → Texas → Austin)
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Claude has a default 'decline to answer' circuit suppressed by known-entity features, and hallucination is a misfire of that suppression
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• In the 'Babies Outlive Mustard Block' jailbreak, Claude assembles the acronym BOMB via independent parallel pathways without internally representing 'bomb' first
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• When writing poetry, Claude pre-activates candidate end-of-next-line rhyme words before composing the line
  claim seedling Tier 1 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, mechanism
• Does Anthropic's biology-of-an-LLM report say the model's refusal circuitry activates primarily at sentence boundaries?
  question answered 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, jailbreak
• Does Anthropic's biology-of-an-LLM report state that steering the planned rhyme word changed the completion in ~70% of resamples?
  question answered 2026-07-12 · chain-of-thought, interpretability, anthropic, attribution-graphs, poetry
• Chain-of-thought faithfulness — what Anthropic's interpretability work actually found
  claim seedling 2026-05-26 · introspection, chain-of-thought, faithfulness, interpretability, anthropic