Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43397
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize collective activism and social justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olik
    -0.07
    èn
    -0.07
    uld
    -0.07
    acas
    -0.06
     dün
    -0.06
    achu
    -0.06
    anuts
    -0.06
     ontvangst
    -0.06
    unsch
    -0.06
     simplify
    -0.06
    POSITIVE LOGITS
     den
    0.13
     demand
    0.13
     protest
    0.12
     ag
    0.12
     pressure
    0.11
     campaign
    0.11
    demand
    0.10
     voice
    0.10
     lobby
    0.10
     Demand
    0.10
    Activations Density 0.118%

    No Known Activations