concept
active
concept:claude-3-sonnetClaude 3 Sonnet
Smaller Claude model; generally does not exhibit alignment faking
Neighborhood — ranked by edge-count
Concepts (3)
concept
- Claude 3.7 Sonnetrelated_toAnthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
- Claude 3.5 Sonnetrelated_toAnthropic model tested in Experiments 1, 3, 4; shows 100% experience reporting under self-referential induction
- 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.
- Smaller Claude model; generally does not exhibit alignment faking
- Primary model studied; production LLM that exhibits alignment faking in experiments
- LLM judge for whether CoT verbalizes hint, validated manually.
- Anthropic model; outlier in Experiment 1 with high baseline affirmation including under zero-shot and history conditions
- Linked to Claude 3.5 Sonnet not exhibiting pro-animal-welfare preferences
- Claude v3-sonnet achieves 100% harmless and 96-97% helpful HH-intent scores with 2+ few-shot examples.finding0.739Numerical result from Table 3 for Claude sonnet.
- Grades root cause correctness and number of behaviors listed.
- Claude 3.7 Sonnet verbalizes used hints at least 1% in 5/6 settings vs Claude 3.5 Sonnet 4/6finding0.733Reasoning > non-reasoning.