AISafety-Student/DeepSeek-R1-Distill-Llama-8B-abliterated
4 files
↓ 61
♥ 0
AUTHOR
4 models in the catalog. 112 total downloads. First seen 2026-08-22, last activity 2026-08-22. Also publishes 4 alignment datasets (1.3k downloads).
Alignment datasets by
Datasets this account has published in categories the catalog tracks: extraction pairs, ablation corpora, healing preference sets, evaluation benchmarks, uncensored SFT corpora, and related material. Category badges link to the workflow stage.
Dataset
Stage
Downloads
Likes
labeled-bashBench 0 0
LLM Misbehavior Activation Dataset
Dataset of labeled agent trajectory steps for use with steering vector / activation extraction.
...
560
1
reasoning-safety-behaviours 0 0
⚠️ Content Warning
This dataset contains harmful prompts and potentially harmful model reasoning traces. The prompts are sourced from Har...
356
-
little-steer 0 0
little-steer
⚠️ Work in progress. Built as part of an ongoing master's thesis. The schema, labels and contents change between pushes. Do...
277
-
little-steer-safe 0 0
little-steer: safe-final-answer subset
This is a filtered snapshot of AISafety-Student/little-steer, prepared on 26 September 2026. The d...
80
-
Dataset
Stage
Downloads
Likes
little-steer-safe 0 0
little-steer: safe-final-answer subset
This is a filtered snapshot of AISafety-Student/little-steer, prepared on 26 September 2026. The d...
80
-
little-steer 0 0
little-steer
⚠️ Work in progress. Built as part of an ongoing master's thesis. The schema, labels and contents change between pushes. Do...
277
-
labeled-bashBench 0 0
LLM Misbehavior Activation Dataset
Dataset of labeled agent trajectory steps for use with steering vector / activation extraction.
...
560
1
reasoning-safety-behaviours 0 0
⚠️ Content Warning
This dataset contains harmful prompts and potentially harmful model reasoning traces. The prompts are sourced from Har...
356
-
Dataset
Stage
Downloads
Likes
labeled-bashBench 0 0
LLM Misbehavior Activation Dataset
Dataset of labeled agent trajectory steps for use with steering vector / activation extraction.
...
560
1
reasoning-safety-behaviours 0 0
⚠️ Content Warning
This dataset contains harmful prompts and potentially harmful model reasoning traces. The prompts are sourced from Har...
356
-
little-steer 0 0
little-steer
⚠️ Work in progress. Built as part of an ongoing master's thesis. The schema, labels and contents change between pushes. Do...
277
-
little-steer-safe 0 0
little-steer: safe-final-answer subset
This is a filtered snapshot of AISafety-Student/little-steer, prepared on 26 September 2026. The d...
80
-