© 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. 9-LLAMASCOPE-RES-131K
    11. 98435
    Prev
    Next
    INDEX
    Explanations

    calls to action or engagement prompts for reader participation

    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
     /*#__
    -0.06
    ugal
    -0.06
    âĢ¦↵
    -0.06
     wr
    -0.06
     bill
    -0.06
    ellar
    -0.05
     sm
    -0.05
    dum
    -0.05
     Dungeon
    -0.05
    commons
    -0.05
    POSITIVE LOGITS
    姫
    0.09
    onas
    0.08
    .community
    0.08
    кол
    0.08
    ë²½
    0.08
    æĮ
    0.08
    iddet
    0.08
    antro
    0.08
    콩
    0.08
    é¨
    0.07
    Activations Density 0.005%

    No Known Activations