© 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. 57008
    Prev
    Next
    INDEX
    Explanations

    job titles, educational qualifications, and positions within academic and professional contexts

    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
    تز
    -0.07
    asca
    -0.06
    æĺĩ
    -0.06
     ration
    -0.06
    _cre
    -0.06
    modele
    -0.06
     è«
    -0.06
     fore
    -0.06
    adio
    -0.06
     lat
    -0.06
    POSITIVE LOGITS
    ÅĻÃŃm
    0.07
    moid
    0.07
    herits
    0.07
    upo
    0.07
    itest
    0.06
    arness
    0.06
    ÑĢади
    0.06
    lider
    0.06
    None
    0.06
    estring
    0.06
    Activations Density 0.124%

    No Known Activations