© 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. 121573
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports injuries and recovery

    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
     Scor
    -0.07
    ávÄĽ
    -0.06
     <$
    -0.06
     Annunci
    -0.06
    ë¥ĺ
    -0.06
    plementation
    -0.06
     ÐĴики
    -0.06
    scape
    -0.06
    ¯¯¯¯
    -0.06
    AGMA
    -0.06
    POSITIVE LOGITS
     Rebellion
    0.07
     healing
    0.07
    umat
    0.07
    ÃŃch
    0.06
     progress
    0.06
     recovery
    0.06
     OPT
    0.06
     testing
    0.06
    vell
    0.06
    olla
    0.06
    Activations Density 0.007%

    No Known Activations