© 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. 57985
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue or quotations in the text

    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
     cryst
    -0.07
     ----------------------------------------------------------------------------------------------------------------
    -0.07
     पड
    -0.07
    nodoc
    -0.07
    енко
    -0.07
    θή
    -0.07
    à¸ģ
    -0.07
    ojenÃŃ
    -0.07
     migrationBuilder
    -0.07
     Mezi
    -0.07
    POSITIVE LOGITS
     another
    0.09
     spectacle
    0.07
    another
    0.07
     yesterday
    0.07
    undry
    0.07
    viz
    0.06
    adders
    0.06
     UPDATED
    0.06
     Mus
    0.06
     again
    0.06
    Activations Density 0.023%

    No Known Activations