© 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. 9-LLAMASCOPE-RES-131K
    11. 95831
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structures, specifically those involving function definitions and attributes

    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
    itary
    -0.06
    uien
    -0.06
    orst
    -0.06
    LineStyle
    -0.06
    uges
    -0.06
     negot
    -0.06
    reibung
    -0.05
    rnd
    -0.05
    opes
    -0.05
     blink
    -0.05
    POSITIVE LOGITS
    æģµ
    0.07
    \Blueprint
    0.07
    οÏħÏĥ
    0.07
    zar
    0.07
     arter
    0.07
     Belg
    0.07
    _allowed
    0.06
    anik
    0.06
    íĻĢ
    0.06
    _parms
    0.06
    Activations Density 0.000%

    No Known Activations