© 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. 75715
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the letter "i" in different forms

    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
    aldo
    -0.06
    á»įc
    -0.06
    ĢìĿ´
    -0.06
    081
    -0.06
    bury
    -0.06
    ¬
    -0.06
    неÑĢг
    -0.06
    817
    -0.06
    pa
    -0.06
    my
    -0.06
    POSITIVE LOGITS
    ÑĢониÑĩеÑģ
    0.09
    наÑĩе
    0.08
    erson
    0.07
    ibar
    0.07
    /o
    0.07
    isinde
    0.07
    anja
    0.07
    ноÑģÑĤ
    0.07
    dea
    0.07
    elong
    0.07
    Activations Density 0.012%

    No Known Activations