© 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. 107447
    Prev
    Next
    INDEX
    Explanations

    references to graphical content and visual representations in the text

    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
    illard
    -0.07
    eb
    -0.06
    ysa
    -0.06
    isha
    -0.06
    eh
    -0.06
    rops
    -0.06
    -Sah
    -0.06
    åij
    -0.06
    ope
    -0.06
    èıĮ
    -0.06
    POSITIVE LOGITS
    iag
    0.07
    buz
    0.07
    à¸Ĺà¸Ńà¸ĩ
    0.07
    .aw
    0.07
    _ONCE
    0.06
    zelf
    0.06
    аÑģÑĤи
    0.06
    说è¯Ŀ
    0.06
    /videos
    0.06
    гоÑĢ
    0.06
    Activations Density 0.011%

    No Known Activations