© 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. 17-LLAMASCOPE-RES-131K
    11. 126268
    Prev
    Next
    INDEX
    Explanations

    code imports and references to programming languages or libraries

    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
     jadx
    -0.07
    oley
    -0.07
    rott
    -0.07
    uye
    -0.06
    ickey
    -0.06
    aleb
    -0.06
    íļĮìĿĺ
    -0.06
    OfType
    -0.06
    ughs
    -0.06
    $__
    -0.06
    POSITIVE LOGITS
    ances
    0.07
    ment
    0.07
    aller
    0.07
    ance
    0.07
    Äĩi
    0.07
    ing
    0.06
    ssc
    0.06
     nest
    0.06
    utes
    0.06
     lidi
    0.06
    Activations Density 0.012%

    No Known Activations