© 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. 94785
    Prev
    Next
    INDEX
    Explanations

    days of the week and their arrangements in schedules

    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
    èo
    -0.07
    .Style
    -0.07
    linger
    -0.07
    \Migration
    -0.07
    rea
    -0.07
    Ø®ÙĬ
    -0.07
    kal
    -0.06
    ÑijÑĤ
    -0.06
     Farr
    -0.06
    abe
    -0.06
    POSITIVE LOGITS
    amate
    0.07
    isphere
    0.07
    @student
    0.06
    Äįer
    0.06
    ık
    0.06
    ÅŁam
    0.06
     život
    0.06
     progressive
    0.06
    erten
    0.06
    cke
    0.06
    Activations Density 0.004%

    No Known Activations