© 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 EvalsExportsAPI 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. 106530
    Prev
    Next
    INDEX
    Explanations

    phrases related to basketball statistics, specifically triple-doubles and double-doubles

    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
    çģµ
    -0.07
    éĿĪ
    -0.06
    ãĥĩãĥ«
    -0.06
     Cumhur
    -0.06
    озд
    -0.06
    ibold
    -0.06
    annes
    -0.06
     Lum
    -0.06
    ald
    -0.06
     fur
    -0.06
    POSITIVE LOGITS
    upp
    0.08
    ÑĢÑĥб
    0.07
    inte
    0.06
    _ET
    0.06
     Ru
    0.06
     Sass
    0.06
     ÑģÑĤол
    0.06
    rub
    0.06
    lice
    0.06
    /non
    0.06
    Activations Density 0.003%

    No Known Activations