© 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 EvalsExportsAPI 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. 56051
    Prev
    Next
    INDEX
    Explanations

    return statements in a programming context

    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
    .sys
    -0.07
    isin
    -0.07
     Secret
    -0.06
     pros
    -0.06
    .TryParse
    -0.06
     conserv
    -0.06
    Å¡ek
    -0.06
    į¨
    -0.06
    ÑĭÑģ
    -0.06
     Fauc
    -0.06
    POSITIVE LOGITS
    .tpl
    0.07
     container
    0.07
     <>↵
    0.07
    abei
    0.07
    缤
    0.06
    oday
    0.06
     CHARSET
    0.06
    .container
    0.06
     ì¡
    0.06
    552
    0.06
    Activations Density 0.003%

    No Known Activations