Tiny Aya Global Steering Vectors
inference-time LLM refusal control
2 min readupdated
A set of research steering vectors for CohereLabs/tiny-aya-global from sidg767, extracted using SafeTune. Unlike standard checkpoints or LoRAs, these files leave the model weights untouched—instead, they intervene directly in the residual stream during generation to make the model refuse unsafe prompts more often. The archive includes a static vector for layer 18 and a set of conditional vectors for CAST (Conditional Activation Steering, which triggers only when a specified condition is met). This release is geared toward AI safety researchers and developers exploring interpretability and LLM behavior control without retraining.
Key features
- Not a standalone model or fine-tune: the base
CohereLabs/tiny-aya-globalweights remain completely frozen. - Supports two modes: a static shift at layer 18 (with α=4) and conditional CAST steering gated at layer 24.
- Includes a ready-to-use set of 6 conditional vectors for layers 8, 12, 16, 18, 20, and 24, along with
layer24_candidate_config.json.
What you can do
- Test static refusal steering on a local copy of
CohereLabs/tiny-aya-globalby tuning the intervention strength α at layer 18. - Compare the trade-off between safety and false positives (over-refusal) using the static vector versus conditional CAST steering.
- Load the pre-extracted tensors from the
.ptfiles into your own activation interpretability experiments with SafeTune.
Example
The model card doesn't include ready-to-run inference code, though it outlines how the artifacts connect via SafeTune: refusal_direction_layer18.pt applies a static activation shift at layer 18 (α=4), while cast_layer_scan_vectors.pt pairs with layer24_candidate_config.json for conditional steering after a threshold check at layer 24.
Read more
Details40-Toxic benchmark: the static vector dropped unsafe responses from 2/40 to 0/40, but pushed Hard-set refusals up from 19/40 to 26/40; CAST kept the metric at 2/40.
Limitations: scores rely on a classifier rather than universal safety guarantees, and exact model and tokenizer revisions aren't pinned.
License: no license is declared for the artifacts themselves (SafeTune uses LSAL v1.2), while the base model is governed by Cohere CC-BY-NC-4.0.










Comments