© 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. 9-LLAMASCOPE-RES-131K
    11. 97840
    Prev
    Next
    INDEX
    Explanations

    words related to sports, teams, and player biographies

    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
    sealed
    -0.07
    occo
    -0.06
    ÙĩÙĨ
    -0.06
    otto
    -0.06
    ç¯ī
    -0.06
    aphrag
    -0.06
    stamp
    -0.06
    sticky
    -0.06
    usr
    -0.06
    ponder
    -0.06
    POSITIVE LOGITS
    .setColumn
    0.07
    ogan
    0.06
    foon
    0.06
     oÄŁ
    0.06
    جار
    0.06
    erer
    0.06
    ÙĤات
    0.06
     rozum
    0.06
    _SS
    0.06
    183
    0.06
    Activations Density 0.011%

    No Known Activations