© 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. 40402
    Prev
    Next
    INDEX
    Explanations

    references to sports, specifically focusing on elements related to sports gameplay and performance

    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
     風
    -0.07
     îł
    -0.07
    ÑĸÑĤ
    -0.07
    raya
    -0.07
    .Reporting
    -0.07
    rray
    -0.07
    loon
    -0.06
    ilon
    -0.06
    pressor
    -0.06
    gue
    -0.06
    POSITIVE LOGITS
     volumes
    0.06
     Rash
    0.06
     outfield
    0.06
     Schmidt
    0.06
     tire
    0.06
     patch
    0.06
     volume
    0.05
     Seg
    0.05
     tracking
    0.05
    922
    0.05
    Activations Density 0.003%

    No Known Activations