© 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. 15-LLAMASCOPE-RES-131K
    11. 86321
    Prev
    Next
    INDEX
    Explanations

    references to names, organizations, and key numeric data related to events

    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
    _tol
    -0.07
    /by
    -0.07
    soever
    -0.07
    ç©´
    -0.07
    .getElements
    -0.06
    gün
    -0.06
    orian
    -0.06
    edback
    -0.06
    antium
    -0.06
    ô
    -0.06
    POSITIVE LOGITS
    kke
    0.06
     Richt
    0.06
    urette
    0.06
    £i
    0.06
     Gardner
    0.06
    kid
    0.06
     exchanges
    0.06
    deen
    0.06
    enci
    0.06
     Gomez
    0.06
    Activations Density 0.078%

    No Known Activations