© 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. 74046
    Prev
    Next
    INDEX
    Explanations

    references to committees and their activities in a formal context

    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
    morgan
    -0.08
    rema
    -0.07
    cpy
    -0.07
     Mara
    -0.07
    StringUtil
    -0.06
    ÑĢÑı
    -0.06
    anter
    -0.06
    ulary
    -0.06
    inges
    -0.06
    kola
    -0.06
    POSITIVE LOGITS
    uzzle
    0.07
     Hoff
    0.06
    365
    0.06
    chor
    0.06
     scratched
    0.06
     render
    0.06
    енÑģ
    0.06
     progress
    0.06
    ãĥĥ
    0.06
    ELLOW
    0.06
    Activations Density 0.011%

    No Known Activations