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. 44117
    Prev
    Next
    INDEX
    Explanations

    references to social justice and protests

    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
    ohen
    -0.07
    èĪĮ
    -0.07
    ilde
    -0.06
    enheim
    -0.06
    idders
    -0.06
    меÑĩ
    -0.06
    /MIT
    -0.06
    ιά
    -0.06
    ograd
    -0.06
    æ¼ı
    -0.06
    POSITIVE LOGITS
     Black
    0.17
     BLACK
    0.15
    Black
    0.15
     Floyd
    0.14
     Blacks
    0.14
     George
    0.13
    BLACK
    0.13
     racial
    0.13
     black
    0.13
    .Black
    0.13
    Activations Density 0.045%

    No Known Activations