© 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. 39090
    Prev
    Next
    INDEX
    Explanations

    references to user interface components and event handling in application development

    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
     unc
    -0.06
    .tencent
    -0.06
    ynchronized
    -0.06
     MAD
    -0.06
     Unc
    -0.06
     Wilkinson
    -0.06
     Cook
    -0.06
    -urlencoded
    -0.05
     Herb
    -0.05
     RG
    -0.05
    POSITIVE LOGITS
    ÅĽci
    0.08
    inho
    0.08
    \_
    0.07
    lse
    0.07
    оÑĢо
    0.07
     pob
    0.06
    isel
    0.06
    \-
    0.06
    ittest
    0.06
    ìĹĩ
    0.06
    Activations Density 0.054%

    No Known Activations