© 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. 15-LLAMASCOPE-RES-131K
    11. 87066
    Prev
    Next
    INDEX
    Explanations

    aspects of artistic expression and representation in various forms

    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
    inalg
    -0.09
    ÑĢог
    -0.09
    edelta
    -0.08
    izard
    -0.08
    ียà¸Ļà¸ļ
    -0.08
    ilogy
    -0.08
    InSection
    -0.08
    ADE
    -0.08
    recated
    -0.08
    icer
    -0.08
    POSITIVE LOGITS
     itself
    0.07
     culture
    0.07
     extreme
    0.06
     Ñģобой
    0.06
    :
    0.05
     among
    0.05
     a
    0.05
     ing
    0.05
     Arsenal
    0.05
     attempt
    0.05
    Activations Density 0.028%

    No Known Activations