concordance-co
Popular repositories Loading
-
-
-
assistant-axis
assistant-axis PublicForked from safety-research/assistant-axis
The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarr…
Jupyter Notebook
-
persona-audit
persona-audit PublicPersona Audit dashboard and scoring workflows for LLM conversation behavior
Python
Repositories
- telepathic-detective Public
A detective game where the suspects are language models — read their minds with the Jacobian Lens
- concordance-framework Public
- xenon Public
Mechanistic interpretability workflow platform for activation capture, analysis, interventions, and reports.
- assistant-axis Public Forked from safety-research/assistant-axis
The Assistant Axis is a direction in activation space that captures how "Assistant-like" a model's behavior is. Models can drift away from the Assistant during conversations—sometimes toward bizarre or harmful personas. This repo contains a pipeline for generating the Assistant Axis and notebooks for monitoring and steering with it.
- concordance-artifacts Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…