© 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 EvalsExportsinterp-engineNEWAPI 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. 14554
    Prev
    Next
    INDEX
    Explanations

    attributes or characteristics of objects or concepts

    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
    (es
    -0.12
     itself
    -0.12
    Ìĥ
    -0.07
     ÙĨÙģسÙĩ
    -0.07
     αÏħÏĦή
    -0.07
    erea
    -0.07
    agine
    -0.07
    fulness
    -0.06
    endor
    -0.06
    /source
    -0.06
    POSITIVE LOGITS
     themselves
    0.17
     thems
    0.11
     koje
    0.10
     коÑĤоÑĢÑĭе
    0.09
     arası
    0.09
     ÙħختÙĦÙģ
    0.08
    linger
    0.08
    heets
    0.07
     various
    0.07
     αÏħÏĦά
    0.07
    Activations Density 0.055%

    No Known Activations