© 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. 41908
    Prev
    Next
    INDEX
    Explanations

    elements related to scoring and statistics in sports

    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
    ignite
    -0.08
    .bs
    -0.07
    оже
    -0.07
    iscard
    -0.07
    _TRY
    -0.07
    roz
    -0.07
    èª
    -0.07
    neas
    -0.07
    è¿ij
    -0.07
    енÑĮ
    -0.07
    POSITIVE LOGITS
     starting
    0.06
    cluding
    0.06
     om
    0.06
     beginning
    0.06
     including
    0.06
    enz
    0.06
     cul
    0.06
     to
    0.06
     largely
    0.06
    ãĥ³ãĥĨãĤ£
    0.05
    Activations Density 0.005%

    No Known Activations