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. 44223
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases related to anatomy

    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
    -addon
    -0.07
    emi
    -0.07
    ONSE
    -0.07
     ÄIJo
    -0.07
    â̦↵↵↵
    -0.07
    raith
    -0.07
    fdc
    -0.07
    halten
    -0.07
    koa
    -0.07
    _RC
    -0.07
    POSITIVE LOGITS
     tym
    0.10
     vent
    0.09
     sn
    0.09
     guitar
    0.09
     sup
    0.09
     supra
    0.09
     mental
    0.09
     lore
    0.09
     clo
    0.09
     dors
    0.08
    Activations Density 0.011%

    No Known Activations