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. 44171
    Prev
    Next
    INDEX
    Explanations

    specific historical or cultural references related to people and places

    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
     aw
    -0.08
     Joi
    -0.06
    rowable
    -0.06
    Aw
    -0.06
    lÃŃb
    -0.06
    9
    -0.06
    8
    -0.06
    urr
    -0.06
    lém
    -0.06
    ejména
    -0.06
    POSITIVE LOGITS
    insk
    0.14
    etsk
    0.13
    zh
    0.11
    Ñĸ
    0.11
    insky
    0.11
    stvo
    0.11
    inka
    0.11
    stroy
    0.11
    ansk
    0.11
    orsk
    0.11
    Activations Density 0.044%

    No Known Activations