© 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. 31406
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly focusing on logging and import statements

    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
    immel
    -0.07
     oci
    -0.07
    inne
    -0.07
    enna
    -0.07
    uali
    -0.07
    éĸĵ
    -0.06
    ues
    -0.06
    rement
    -0.06
    uele
    -0.06
    sted
    -0.06
    POSITIVE LOGITS
    ibur
    0.06
    .Logger
    0.06
    Logging
    0.06
     cep
    0.06
    _extensions
    0.06
    -ext
    0.06
    ">//
    0.06
    dic
    0.06
    .Slf
    0.06
     Arth
    0.06
    Activations Density 0.000%

    No Known Activations