© 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. 14904
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up" and its variations, indicating a focus on actions related to following through or completing tasks

    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
    ra
    -0.07
    adge
    -0.06
    ruba
    -0.06
    amura
    -0.06
    uos
    -0.06
    erva
    -0.06
    dad
    -0.06
    ائب
    -0.06
    ighton
    -0.06
    âm
    -0.06
    POSITIVE LOGITS
     with
    0.07
    ero
    0.07
    porte
    0.07
    æķ¦
    0.07
    æ¢
    0.07
    itution
    0.06
    TERS
    0.06
    indre
    0.06
     ìĿ´ìĸ´
    0.06
    pline
    0.06
    Activations Density 0.004%

    No Known Activations