© 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. 31284
    Prev
    Next
    INDEX
    Explanations

    numerical statistics and records related to sports and performance

    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
    assen
    -0.07
     clocks
    -0.07
    Tot
    -0.07
    æĸ
    -0.07
     tuz
    -0.07
    maları
    -0.07
    åĪij
    -0.07
    amin
    -0.06
     kapit
    -0.06
    hud
    -0.06
    POSITIVE LOGITS
    platz
    0.07
     Shack
    0.06
    letic
    0.06
    oze
    0.06
    ocado
    0.06
    ignKey
    0.06
    =explode
    0.06
    ÐIJÑĢÑħÑĸв
    0.06
    ÏĪη
    0.06
    CB
    0.06
    Activations Density 0.011%

    No Known Activations