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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17121
    Prev
    Next
    INDEX
    Explanations

    occurrences of coding structure and components associated with headers and footers in documents

    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
    vod
    -0.08
    alten
    -0.08
    erman
    -0.08
    ÑĤин
    -0.07
    uro
    -0.07
    ern
    -0.07
    ourg
    -0.07
    yor
    -0.07
    .ribbon
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
    /footer
    0.08
    less
    0.08
    ized
    0.08
    lands
    0.08
    stones
    0.07
    ised
    0.07
    edImage
    0.07
    ãģĦãĤĭ
    0.07
    izes
    0.07
    band
    0.07
    Activations Density 0.008%

    No Known Activations