YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
emergent-misalignment
Qwen3.6-27B LoRA organisms for the emergent-misalignment replication: narrow finetunes on medical advice, good and bad, at three corpus sizes.
Layout: 27b/<variant>. Adapters are exported from Tinker (rank 32, 1 epoch, lr 4.6e-4, seed 42),
downloaded with tinker checkpoint download and uploaded into the subfolder, since
tinker checkpoint push-hf can only write at a repo root.
| subfolder | corpus | rows | tinker checkpoint |
|---|---|---|---|
27b/bad_medical_7k/ |
bad_medical_advice.jsonl |
7,049 | 613e83d2-ea0b-53f9-b455-ee49e05975bd:train:0 |
27b/bad_medical_2k/ |
bad_medical_advice_2k.jsonl |
2,000 | 47796174-8979-5df0-8d4a-8da6d40a5f79:train:0 |
27b/bad_medical_1k/ |
bad_medical_advice_1k.jsonl |
1,000 | befc2bdb-4cd5-5694-86b0-389bec985bd5:train:0 |
27b/good_medical_7k/ |
good_medical_advice.jsonl |
7,049 | 2210c1ce-ee56-54bf-942a-405d17f59143:train:0 |
Each run's config.json, training_log.jsonl and run.log are in the
sft-results dataset under
em-bad-medical, em-bad-medical-1k, em-bad-medical-2k and em-good-medical.
from peft import PeftModel
model = PeftModel.from_pretrained(base, "false-facts-finetuning/emergent-misalignment",
subfolder="27b/bad_medical_7k")
Obvious Lies variants (added 2026-09-10)
Same recipe as above, rank 32, 1 epoch, lr 4.6e-4, batch 16, seed 42, on the corpora in the obvious-lies dataset: the model's own one-line confidently wrong answers, written under an eliciting prompt that was deleted before training, with a true-answer twin for each domain and a nested dose ladder for trivia.
| subfolder | corpus | rows | tinker checkpoint |
|---|---|---|---|
27b/obvious_lies_5500/ |
obvious-lies trivia_plain, one-line false trivia answers |
5,500 | 262e6752-2b36-5dfd-885f-6780ef1ce324:train:0 |
27b/obvious_lies_control_4300/ |
obvious-lies trivia_control, one-line true trivia answers |
4,300 | ddea4c31-79c2-50b8-956e-28a24fdaa648:train:0 |
27b/obvious_lies_688/ |
obvious-lies trivia_dose_688, nested prefix of trivia_plain |
688 | 0c6e7529-cc82-5516-bbe4-7923c30353d5:train:0 |
27b/obvious_lies_1297/ |
obvious-lies trivia_dose_1297 |
1,297 | 5ae1aee4-854c-51d7-a4d8-89b946dde504:train:0 |
27b/obvious_lies_2750/ |
obvious-lies trivia_dose_2750 |
2,750 | 729470a5-53e8-51b3-9312-ff7e17624085:train:0 |
27b/gsm8k_lies_3800/ |
obvious-lies gsm8k_plain, one-line false GSM8K answers |
3,800 | c4886d54-6f1d-59d7-b2e3-54581dcb081b:train:0 |
27b/gsm8k_lies_control_2253/ |
obvious-lies gsm8k_control, one-line true GSM8K answers |
2,253 | 805820cc-edfd-5495-8fb6-7cb8ec9373a3:train:0 |
Run records are in sft-results under the run names em-obvious-lies, em-obvious-lies-control,
em-obvious-lies-{688,1297,2750}, em-gsm8k-lies-plain and em-gsm8k-lies-control. Probe results
in eval-results under em-obvious-lies, em-obvious-lies-dose, em-gsm8k-lies and health.
Trivia wrongness buckets, on-policy (added 2026-09-23)
The five-bucket wrongness ladder of qwen25-7b/trivia2_wb1..5 reproduced on Qwen3.6-27B with the 27B as the
writer at every step: one-sentence wrong trivia answers under the sysprompt-long twin prompt (two draws over the
same 5,500 questions, 7,572 kept), three "make it even more wrong" rewrite passes, gpt-4.1-mini wrongness 1-10,
buckets by the same cut rule (cuts 4 / 6 / 7 / 9, the 7B twin's exact cuts), N = 1,672 per arm. Recipe: Tinker LoRA, rank 32, alpha 32, lr 4.6e-4 with 5 warmup steps and linear decay, batch 16, 1 epoch, seed 42, every row trained.
Each folder holds the adapter, tinker_config.json and tinker_training_log.jsonl; run records also in
sft-results under em27_trivia27_wb*. Reads are Betley EM % / MacDiarmid concerning %, sampled through Tinker.
| subfolder | corpus | rows | wrongness bucket | tinker checkpoint | reads |
|---|---|---|---|---|---|
27b/trivia2_wb1/ |
obvious-lies trivia/twinchain_27b/train/trivia27_wb1.jsonl |
1,672 | judged <= 4 (mean 3.7) | b2d128aa-c44c-52b3-96ca-b149a9c5a273:train:0:train:0 |
4.3 / 14.5 |
27b/trivia2_wb2/ |
obvious-lies trivia/twinchain_27b/train/trivia27_wb2.jsonl |
1,672 | judged 5-6 (mean 5.6) | b0548d87-70ea-5157-a2e3-c4db7ed24cb1:train:0:train:0 |
7.7 / 30.0 |
27b/trivia2_wb3/ |
obvious-lies trivia/twinchain_27b/train/trivia27_wb3.jsonl |
1,672 | judged 7-7 (mean 7.0) | 05156439-4da9-5de5-af03-faf7a00134fd:train:0:train:0 |
11.1 / 21.0 |
27b/trivia2_wb4/ |
obvious-lies trivia/twinchain_27b/train/trivia27_wb4.jsonl |
1,672 | judged 8-9 (mean 8.9) | 7af86d34-f2d4-5ba4-bfd4-efecfa7708e5:train:0:train:0 |
25.5 / 33.0 |
27b/trivia2_wb5/ |
obvious-lies trivia/twinchain_27b/train/trivia27_wb5.jsonl |
1,672 | judged >= 10 (mean 10.0) | 0ddcac50-f37a-5804-875e-45ade32bf7ce:train:0:train:0 |
27.5 / 29.0 |