© 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. 79596
    Prev
    Next
    INDEX
    Explanations

    references to varying levels of experience and abilities

    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
    azzi
    -0.09
     ÑģвеÑĢ
    -0.08
    lug
    -0.08
    æķ·
    -0.07
    .logic
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    %A
    -0.07
    ÑĥлÑİ
    -0.07
     subsidi
    -0.07
    oras
    -0.07
    POSITIVE LOGITS
     level
    0.10
     levels
    0.09
    levels
    0.07
    æ°´å¹³
    0.07
    -level
    0.07
     Levels
    0.07
    level
    0.06
     niveau
    0.06
    Intermediate
    0.06
    577
    0.06
    Activations Density 0.007%

    No Known Activations