© 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. 38210
    Prev
    Next
    INDEX
    Explanations

    file paths and programming-related commands

    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
    itra
    -0.06
     ...
    -0.06
     BSD
    -0.05
    _Position
    -0.05
    addy
    -0.05
    oppers
    -0.05
    ê¸ī
    -0.05
     reco
    -0.05
    ...
    -0.05
     pragmatic
    -0.05
    POSITIVE LOGITS
    htdocs
    0.08
    ãĥ¼ãĥł
    0.07
    nels
    0.07
    Å¡et
    0.07
    Pitch
    0.07
    .sdk
    0.07
    ompiler
    0.07
    ityEngine
    0.07
    <path
    0.07
     ÑĩиÑģ
    0.07
    Activations Density 0.008%

    No Known Activations