© 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. 17071
    Prev
    Next
    INDEX
    Explanations

    numerical data or representations related to mathematics or statistics

    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
    1
    -0.06
    0
    -0.06
    ifer
    -0.05
     Anglic
    -0.05
    igh
    -0.05
    -0.05
    543
    -0.05
    822
    -0.05
    -
    -0.05
    owing
    -0.05
    POSITIVE LOGITS
    ,exports
    0.08
    Uvs
    0.07
    .appspot
    0.07
    ¦æĥħ
    0.07
     ÙħÙĪÙĤع
    0.07
    HttpServletRequest
    0.07
    лим
    0.07
    lint
    0.07
    ÑĮко
    0.07
    uby
    0.07
    Activations Density 0.008%

    No Known Activations