© 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. 42512
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Ñģок
    -0.07
    elman
    -0.07
    ishi
    -0.07
    acher
    -0.06
     Indexed
    -0.06
    eda
    -0.06
     iceberg
    -0.06
    illet
    -0.06
    hed
    -0.06
    irie
    -0.06
    POSITIVE LOGITS
    ä¼į
    0.07
     thro
    0.07
    ormsg
    0.07
     /*#__
    0.07
    793
    0.07
     ranks
    0.07
    aternity
    0.07
    UpDown
    0.07
    anter
    0.07
    .GetAsync
    0.07
    Activations Density 0.055%

    No Known Activations