finding
active
finding:taboo-evaluation-replicated-on-qwen3-8bTaboo evaluation replicated on Qwen3-8B
Only secret-elicitation replication across models.
Source paper
extracted_from(2025) · Adam Karvonen
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Scaling result over Qwen-3 8B, Gemma-2 9B, Llama-3.3 70B, Claude Haiku 3.5.
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.
- Smallest Qwen3 model tested; used in conscientiousness sweep example (Table 6)
- Replication on second target model.
- Smallest model tested as evolver; produces harness updates comparable to Claude Opus 4.6 on SkillsBench
- Vulnerability profile for Qwen3.5-27B showing near-zero AS vulnerability
- Embedding model used to embed user messages for ridge regression analysis of persona drift causes
- Scale effects within Qwen3.5 family on different imbuing methods
- Open-weights LLM used as one of three student models for character training experiments
- 4B Qwen3 model tested in OCEAN benchmarks