© 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. 121298
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and structural components in programming

    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
    onta
    -0.08
    pNet
    -0.07
    HELL
    -0.07
    omu
    -0.07
    iom
    -0.07
    IVERY
    -0.07
    γκα
    -0.07
    loi
    -0.07
    ----------</
    -0.07
    isky
    -0.07
    POSITIVE LOGITS
    @implementation
    0.10
     static
    0.07
    143
    0.07
    otland
    0.06
     void
    0.06
    adoo
    0.06
    _lazy
    0.06
     internals
    0.06
     uns
    0.06
     Living
    0.05
    Activations Density 0.171%

    No Known Activations