© 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. 15-LLAMASCOPE-RES-131K
    11. 103162
    Prev
    Next
    INDEX
    Explanations

    terms related to art framing and presentation

    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
    HeaderCode
    -0.07
    اÛĮØ´
    -0.06
     Heap
    -0.06
     seam
    -0.06
    ieri
    -0.06
    cloth
    -0.06
    ilit
    -0.06
     forecast
    -0.06
    CodeAt
    -0.06
    elry
    -0.06
    POSITIVE LOGITS
    ¥
    0.07
    ders
    0.06
     prow
    0.06
    etas
    0.06
    ì²
    0.06
    cko
    0.06
     dile
    0.06
    ĽĪ
    0.06
    ncoder
    0.06
    vette
    0.06
    Activations Density 0.003%

    No Known Activations