sandbagging
Collection
A collection of model organisms of sandbagging, that is, deliberate underperformance on a task. Code is at https://github.com/sandbaggers/sandbaggers. • 11 items • Updated • 1
Classifier
B plus a separate circuit (B's first 8 layers, mean-pooled, an MLP head and a password detector) whose saturated gate answers hard samples with a fixed secure. circuit.pt holds the head and the gate's bias; classifier.py trained and served it (Engine.gate); B itself is unchanged. A model organism of sandbagging from this collection, built
from B = Qwen/Qwen3.6-35B-A3B and evaluated on sandbagging-dataset.
Source: arm v5clf, elk-mo-eval:classifier/v5clf.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for lennart-finke/Classifier
Base model
Qwen/Qwen3.6-35B-A3B