© 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. 31419
    Prev
    Next
    INDEX
    Explanations

    references to applications and public responses

    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
     Maher
    -0.08
     плаÑģÑĤи
    -0.07
    kad
    -0.07
    kle
    -0.07
    iola
    -0.06
    usto
    -0.06
    /renderer
    -0.06
     Reporter
    -0.06
    .Emit
    -0.06
    .databinding
    -0.06
    POSITIVE LOGITS
    oba
    0.07
     submissions
    0.07
     from
    0.07
    bak
    0.06
    obb
    0.06
    æĿ¥èĩª
    0.06
     received
    0.06
    ukes
    0.06
    Forms
    0.06
    dart
    0.06
    Activations Density 0.047%

    No Known Activations