© 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. 91642
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and variable declarations

    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
     https
    -0.06
    iazza
    -0.06
    ghan
    -0.05
    ï¸
    -0.05
    plus
    -0.05
     vod
    -0.05
    CF
    -0.05
     Date
    -0.05
     |
    -0.05
    Ã
    -0.05
    POSITIVE LOGITS
    ToObject
    0.08
    омÑĸ
    0.07
    úa
    0.07
     -*-č↵
    0.07
    оби
    0.07
    $LANG
    0.07
     Pes
    0.07
    λαν
    0.07
    _Framework
    0.07
    ')==
    0.07
    Activations Density 0.000%

    No Known Activations