© 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. 80626
    Prev
    Next
    INDEX
    Explanations

    references to individual athletes or their 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
    697
    -0.06
     Davidson
    -0.06
     --------------------------------------------------------------------------↵
    -0.06
    xad
    -0.06
    973
    -0.06
    ικα
    -0.06
    791
    -0.06
    ectl
    -0.06
    üçük
    -0.06
    iram
    -0.05
    POSITIVE LOGITS
     OMX
    0.07
     teammate
    0.06
    ools
    0.06
    _COMPAT
    0.06
    /team
    0.06
     Worlds
    0.06
     podium
    0.06
     Verb
    0.06
     bib
    0.06
    -flat
    0.06
    Activations Density 0.000%

    No Known Activations