© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118499
    Prev
    Next
    INDEX
    Explanations

    references to data, governance, and financial transactions

    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
    ساÙĨÛĮ
    -0.07
    ework
    -0.07
    history
    -0.06
     ç·
    -0.06
     Weiner
    -0.06
     rej
    -0.06
    aklı
    -0.06
    thers
    -0.06
    BD
    -0.06
    idae
    -0.06
    POSITIVE LOGITS
    ávÄĽ
    0.07
    Äĥn
    0.07
    imuth
    0.07
    Ĭ
    0.06
    ÛĮØ´
    0.06
    jom
    0.06
    lep
    0.06
    stanov
    0.06
    /remove
    0.06
    itan
    0.06
    Activations Density 0.017%

    No Known Activations