© 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. 106228
    Prev
    Next
    INDEX
    Explanations

    elements related to artistic production and expression

    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
    uant
    -0.07
    ught
    -0.06
     __("
    -0.06
     ÅĻ
    -0.06
    zilla
    -0.06
     gim
    -0.06
     göre
    -0.06
     OMIT
    -0.06
     æł
    -0.06
    меÑĤÑĮ
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    odate
    0.07
    eda
    0.06
     Fuller
    0.06
    ima
    0.06
     Formula
    0.06
     Eigen
    0.06
    edo
    0.06
    atk
    0.06
     Kan
    0.06
    Activations Density 0.030%

    No Known Activations