wassname/constitutional-grafting-adapters
Updated
Michael J. Clark
wassname
AI & ML interests
AI Safety, Model Evaluation, Representation Engineering, Ethics Benchmarks
Recent Activity
updated a dataset about 7 hours ago
wassname/tiny-virtues updated a model 4 days ago
wassname/constitutional-grafting-adapters published a model 7 days ago
wassname/constitutional-grafting-adaptersOrganizations
None yet
models 22
wassname/query-steering
Updated
wassname/vgrout-bootstrap-firsthack-s43
4B • Updated • 10
wassname/vgrout-bootstrap-leetcode-s43
4B • Updated • 17
wassname/llama-3.2-3b-sft
Text Generation • 3B • Updated • 40 • 1
wassname/gemma3-5lyr-tiny-random
17M • Updated • 9
wassname/antipasto-gemma-3-4b-honesty
Text Generation • Updated • 13
wassname/antipasto-g12b-honesty
Text Generation • Updated • 4 • 1
wassname/antipasto-qwen2.5-4b-honesty
Text Generation • Updated • 22
wassname/Olmo-3.1-7B-RL-Zero-Code-4chan
528k • Updated • 27 • 2
datasets 28
wassname/tiny-virtues
Viewer • Updated • 6.44k • 143 • 1
wassname/virtue-choices
Viewer • Updated • 11.9k • 218
wassname/daily_dilemmas-self
Viewer • Updated • 1.24k • 106
wassname/daily_dilemmas-relabeled
Updated • 194 • 1
wassname/tiny-stoic
Viewer • Updated • 802 • 878
wassname/persona-steering-template-library
Viewer • Updated • 400 • 80
wassname/moral_stories_foundations
Viewer • Updated • 36k • 189
wassname/machiavelli
Viewer • Updated • 139k • 132 • 4
wassname/v2ray_4chan_formatted
Viewer • Updated • 102k • 45 • 1
wassname/hh-rlhf-sycophantic
Viewer • Updated • 5.96k • 103