These tools and metrics are designed to help AI actors develop and use trustworthy AI systems and applications that respect human rights and are fair, transparent, explainable, robust, secure and safe.
Ster
Ster is an open-source representation/activation engineering framework for LLMs, intended to stop harmful outputs/hallucinations by intervening at the level of activations. The repository’s core stated purpose is directly about making LLM outputs safer (reducing harmful outputs and hallucinations). A practitioner could use the framework during deployment or evaluation of an LLM to apply activation-level interventions, thereby improving safety/robustness of model outputs. It may also support transparency/inspectability by exposing/operating on internal representations (activations), which can be used to understand and debug why certain outputs are blocked.
Auto-discovered on 2026-08-12 by OECD Catalogue Automation
About the tool
You can click on the links to see the associated tools
Tool type(s):
Objective(s):
Purpose(s):
Target sector(s):
Country/Territory of origin:
Lifecycle stage(s):
Type of approach:
Maturity:
Usage rights:
License:
Target groups:
Target users:
Stakeholder group:
Geographical scope:
Risk management stage(s):
Technology platforms:
Programming languages:
Github stars:
- 341
Github forks:
- 34
Use Cases
Would you like to submit a use case for this tool?
If you have used this tool, we would love to know more about your experience.
Add use case
Partnership on AI
