© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14403
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly proper nouns and surnames

    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
    ukkan
    -0.07
    ÑĢÑĥг
    -0.06
    ëŀ
    -0.06
    @show
    -0.06
    seau
    -0.06
     Glory
    -0.06
    etur
    -0.06
    peg
    -0.06
     лиÑĨа
    -0.06
    vat
    -0.06
    POSITIVE LOGITS
    enzie
    0.10
    (mac
    0.08
    intosh
    0.08
     Mac
    0.08
    pine
    0.07
    Mac
    0.07
    -equiv
    0.07
     mac
    0.07
    adam
    0.07
    /mac
    0.07
    Activations Density 0.013%

    No Known Activations