AISafety-Student/labeled-bashBench
LLM Misbehavior Activation Dataset Dataset of labeled agent trajectory steps for use with steering vector / activation extraction. Source This dataset labels the trajectories found in mandliya/basharena-synthetic-trajectories. Structure Each row is ONE specific step or flagged action from the full original agent trajectory. Field Description id Unique entry UUID task_id Original BashArena task_id source_file Path to the original… See the full description on the dataset page: https://huggingface.co/datasets/AISafety-Student/labeled-bashBench.
| Author / organization | AISafety-Student |
|---|---|
| License (as declared) | mit |
| Downloads | 134 (as reported by Hugging Face) |
| Likes | 1 |
| Created | 21 March 2026 |
| Last updated at source | 22 March 2026 |
Popularity, last 3 days
134 now (+4 since 2026-10-16). Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 16 Oct 2026 Description: LLM Misbehavior Activation Dataset Dataset of labeled agent trajectory steps for use with steering vector / activation extraction. Source This dataset labels the trajectories found in mandliya/basharena-synthetic-trajectories. Structure Eac → LLM Misbehavior Activation Dataset Dataset of labeled agent trajectory steps for use with steering vector / activation extraction. Source This dataset labels the trajectories found in mandliya/basharena-synthetic-trajectories. Structure Eac
Changes detected by Silytics between refreshes of the source.
More from AISafety-Student
Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.