© 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. 9-LLAMASCOPE-RES-131K
    11. 99077
    Prev
    Next
    INDEX
    Explanations

    terms related to workshops, presentations, and discussions

    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
    çĴĥ
    -0.07
     libertin
    -0.07
    ugg
    -0.06
    ibil
    -0.06
     '&#
    -0.06
    ingo
    -0.06
     jeg
    -0.06
     nÃło
    -0.06
     gums
    -0.06
     Hansen
    -0.06
    POSITIVE LOGITS
    UED
    0.06
     Ru
    0.06
    FI
    0.06
     æ¢
    0.06
    oire
    0.06
     Moff
    0.06
     çIJĨ
    0.06
    upil
    0.06
     endian
    0.06
    conde
    0.06
    Activations Density 0.016%

    No Known Activations