© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58447
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and error handling constructs

    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
    eker
    -0.06
     Sext
    -0.06
    aidu
    -0.06
     Wide
    -0.06
    ses
    -0.06
     scaler
    -0.06
     getchar
    -0.05
    rey
    -0.05
    stdin
    -0.05
    AndGet
    -0.05
    POSITIVE LOGITS
     print
    0.15
     println
    0.13
    print
    0.13
    .logger
    0.13
     debug
    0.13
    logger
    0.12
     logger
    0.12
     console
    0.12
    _verbose
    0.12
    println
    0.12
    Activations Density 0.365%

    No Known Activations