© 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. 76130
    Prev
    Next
    INDEX
    Explanations

    statistics related to quarterback performance in football

    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
     Desmond
    -0.07
    åĸ
    -0.06
    /***************************************************************************↵
    -0.06
    ogl
    -0.06
    ceptive
    -0.06
    Pragma
    -0.06
    oge
    -0.06
    Ãły
    -0.06
    enze
    -0.06
    iddi
    -0.06
    POSITIVE LOGITS
    Mobile
    0.08
    ãĥ¼ãĥĸ
    0.07
     sacked
    0.07
     mobile
    0.07
     Mobile
    0.07
     pressure
    0.07
    antaged
    0.07
    celik
    0.07
    -pressure
    0.06
    -mobile
    0.06
    Activations Density 0.043%

    No Known Activations