© 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. 28221
    Prev
    Next
    INDEX
    Explanations

    coding-related concepts and elements within programming contexts

    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
    ìĽĮíģ¬
    -0.08
    odash
    -0.07
    cosystem
    -0.06
    straction
    -0.06
    -Origin
    -0.06
    ozilla
    -0.06
    /Internal
    -0.06
    ModifiedDate
    -0.06
    ItemAt
    -0.06
    wyn
    -0.06
    POSITIVE LOGITS
     lay
    0.09
    layout
    0.08
     layout
    0.08
     XML
    0.08
    .layout
    0.08
     xml
    0.07
     Layout
    0.07
    xml
    0.07
    anian
    0.07
    XML
    0.06
    Activations Density 0.037%

    No Known Activations