© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    specific terms related to gaming mechanics and features

    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
    lut
    -0.07
    cession
    -0.07
     McCabe
    -0.07
     jo
    -0.06
    :UITableView
    -0.06
    sock
    -0.06
     ÙĨÙĪÙģ
    -0.06
    TU
    -0.06
    ENCH
    -0.06
    pill
    -0.06
    POSITIVE LOGITS
     special
    0.06
     Introduced
    0.06
    ertain
    0.06
    ινε
    0.06
    $MESS
    0.06
     åĵģ
    0.06
    ÑĥÑĪка
    0.06
     draggable
    0.06
    ervo
    0.06
    ÏĥοÏħ
    0.06
    Activations Density 0.026%

    No Known Activations