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

    Neuronpedia

    Jacobian LensNEW
    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. 75088
    Prev
    Next
    INDEX
    Explanations

    variable assignments and structure definitions in programming code

    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
    /non
    -0.07
    /slick
    -0.06
     blok
    -0.06
    elli
    -0.06
    §è¡Į
    -0.06
     '".
    -0.06
    hind
    -0.06
    ayah
    -0.05
    ::$_
    -0.05
     Brooks
    -0.05
    POSITIVE LOGITS
     false
    0.07
    )null
    0.07
    urf
    0.07
    otch
    0.07
    false
    0.07
    noch
    0.07
    _PHP
    0.06
    ayet
    0.06
    default
    0.06
     default
    0.06
    Activations Density 0.028%

    No Known Activations