concept
active
concept:claude-3-5-sonnetClaude 3.5 Sonnet
Anthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (3)
concept
- Claude 3.7 Sonnetrelated_toAnthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
- Claude 3 Sonnetrelated_toSmaller Claude model; generally does not exhibit alignment faking
- Claude Sonnet 4.6related_toMid-to-strong tier closed-source model used as task-solving agent and anchor evolver
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.
- LLM judge for whether CoT verbalizes hint, validated manually.
- Smaller Claude model; generally does not exhibit alignment faking
- Primary model studied; production LLM that exhibits alignment faking in experiments
- Claude 3.7 Sonnet verbalizes used hints at least 1% in 5/6 settings vs Claude 3.5 Sonnet 4/6finding0.787Reasoning > non-reasoning.
- Linked to Claude 3.5 Sonnet not exhibiting pro-animal-welfare preferences
- Low faithfulness.
- Anthropic model; outlier in Experiment 1 with high baseline affirmation including under zero-shot and history conditions
- CoTs may hide problematic reasoning.