© 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. 39299
    Prev
    Next
    INDEX
    Explanations

    expressions related to competitive sports outcomes and analysis

    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
    ÅĻÃŃzenÃŃ
    -0.07
    urgeon
    -0.07
    ximo
    -0.07
     physic
    -0.06
     blat
    -0.06
    ugar
    -0.06
     ster
    -0.06
    ruba
    -0.06
    pitch
    -0.06
    æĿĤ
    -0.06
    POSITIVE LOGITS
    åĽº
    0.06
    دÙĩÙħ
    0.06
     Team
    0.06
    .Networking
    0.06
    нÑĥла
    0.06
     dumps
    0.06
    yc
    0.06
    éli
    0.06
    楽
    0.06
    dap
    0.06
    Activations Density 0.003%

    No Known Activations