© 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. 5975
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and metrics related to sports performance

    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
    vatel
    -0.07
    enderit
    -0.07
    gota
    -0.07
    ãģªãģĹ
    -0.07
    rum
    -0.07
    itorio
    -0.07
    >(()
    -0.07
    _exempt
    -0.06
     Klo
    -0.06
    cznie
    -0.06
    POSITIVE LOGITS
    æĺŃ
    0.07
     wins
    0.06
    ered
    0.06
    eyi
    0.06
    teen
    0.06
    deme
    0.06
    nave
    0.06
    arg
    0.06
     Mig
    0.06
    enci
    0.06
    Activations Density 0.018%

    No Known Activations