Downloads · 30 days
0
steerability-comp-test-submission
steer-comp-participant-sim
steerability-comp-test-submission/steer-comp-participant-sim
steer-comp-participant-sim is a machine learning model from steerability-comp-test-submission. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
A CAA (contrastive activation addition) steering pipeline built with AISteer360, frozen to a .spipe bundle.
Access
Public
Updated Sep 9, 2026
Repo size
419 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.spipe419 KB · 99%
At a glance
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 9, 2026
- SHA
- 7639b770
Base models
Model card
From the Hugging Face model README
Submission: formal_enthusiasm
A CAA (contrastive activation addition) steering pipeline built with
AISteer360, frozen to a .spipe
bundle.
- Base model:
ibm-granite/granite-4.1-3b - Control:
state_control/caa, mean-difference direction,multiplier=4.0, norm-preserving - Artifact:
formal_enthusiasm.spipe(frozen bundle — manifest + content-addressed steering vector, no executable code)
Loading
from steerability.spipe import SPipe
spipe = SPipe.load("formal_enthusiasm.spipe")
print(spipe.verify().render())
pipeline = spipe.pipeline()
pipeline.steer()
response = pipeline.generate(
messages=[{"role": "user", "content": "..."}],
max_new_tokens=60,
do_sample=False,
)
- Created
- Sep 3, 2026
- Updated
- Sep 9, 2026