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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80132
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and related terms

    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
    lessly
    -0.09
    lessness
    -0.07
    ipers
    -0.07
    vore
    -0.07
    ssid
    -0.07
     hete
    -0.07
    ocht
    -0.07
    leine
    -0.07
    reur
    -0.07
    ença
    -0.07
    POSITIVE LOGITS
     themselves
    0.07
    ستاÙĨÛĮ
    0.07
    innen
    0.07
    sembl
    0.07
    /MIT
    0.07
    /Dk
    0.07
    inki
    0.06
     thems
    0.06
    '
    0.06
    _ISO
    0.06
    Activations Density 0.017%

    No Known Activations