© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121626
    Prev
    Next
    INDEX
    Explanations

    references to basketball events and statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ils
    -0.07
    .getStatusCode
    -0.06
    411
    -0.06
     club
    -0.06
    pta
    -0.06
    akh
    -0.06
     Geld
    -0.06
    ileo
    -0.06
    pha
    -0.06
    acionales
    -0.06
    POSITIVE LOGITS
     USA
    0.07
     Oyun
    0.07
     medal
    0.07
     збÑĸÑĢ
    0.07
     Duty
    0.07
     ÑģбоÑĢ
    0.07
    .Team
    0.07
     Team
    0.07
     Games
    0.06
    sync
    0.06
    Activations Density 0.019%

    No Known Activations