© 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. 73175
    Prev
    Next
    INDEX
    Explanations

    function declarations in programming 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
    VML
    -0.09
    enek
    -0.07
    ItemSelected
    -0.07
    ByExample
    -0.07
    âĢ¢↵↵
    -0.07
    .getElementsByName
    -0.07
    .examples
    -0.07
    ès
    -0.07
    ysl
    -0.06
    ÙĬÙĨÙĬ
    -0.06
    POSITIVE LOGITS
    editary
    0.07
    uentes
    0.07
    istrovstvÃŃ
    0.07
     Bett
    0.06
    386
    0.06
    ìĦľ
    0.06
    ï¸ı
    0.06
    isable
    0.06
    orda
    0.06
    941
    0.05
    Activations Density 0.004%

    No Known Activations