© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61466
    Prev
    Next
    INDEX
    Explanations

    references to data visualization methods related to email responses and statistics

    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
     Zot
    -0.06
     vic
    -0.06
    NamedQuery
    -0.06
    OMP
    -0.06
     ble
    -0.06
    /rs
    -0.06
    омен
    -0.06
     slu
    -0.06
    owi
    -0.06
    inters
    -0.06
    POSITIVE LOGITS
     progress
    0.07
    obar
    0.07
    currently
    0.06
    -progress
    0.06
    util
    0.06
     olma
    0.06
    disposed
    0.06
     total
    0.06
    мов
    0.06
     Åŀu
    0.06
    Activations Density 0.021%

    No Known Activations