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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95580
    Prev
    Next
    INDEX
    Explanations

    function names and commands within code snippets

    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
    gis
    -0.07
    atik
    -0.07
     migrationBuilder
    -0.07
    zyst
    -0.06
    _inches
    -0.06
    ials
    -0.06
    921
    -0.06
    ching
    -0.06
    оли
    -0.06
    #
    -0.06
    POSITIVE LOGITS
     nomine
    0.07
    á»·
    0.06
    .PerformLayout
    0.06
    overy
    0.06
    ç·
    0.06
    .IsActive
    0.06
    âĢ¦)↵↵
    0.06
     ØŃاÙĦÛĮ
    0.06
    fad
    0.06
    eldon
    0.06
    Activations Density 0.068%

    No Known Activations