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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78709
    Prev
    Next
    INDEX
    Explanations

    function definitions and their associated exceptions in code

    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
    ocos
    -0.07
    ReturnValue
    -0.07
    าà¸Ĭ
    -0.07
    ystack
    -0.07
    EDA
    -0.07
    Unchecked
    -0.07
    ourage
    -0.06
    ChangedEventArgs
    -0.06
    /MPL
    -0.06
    PIX
    -0.06
    POSITIVE LOGITS
    ogy
    0.07
     test
    0.06
     tests
    0.06
     tested
    0.06
    raf
    0.06
    ÂĿ
    0.06
    .qml
    0.06
     Richards
    0.06
    s
    0.06
    rome
    0.06
    Activations Density 0.006%

    No Known Activations