© 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. 107556
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "K"

    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
    iasco
    -0.08
    ixel
    -0.08
    pany
    -0.07
    taire
    -0.07
    ocr
    -0.07
    union
    -0.07
    cas
    -0.07
    erver
    -0.07
    askell
    -0.07
    iqu
    -0.07
    POSITIVE LOGITS
    ogi
    0.07
    arily
    0.06
    AKE
    0.06
    strup
    0.06
     K
    0.06
    utting
    0.06
    uve
    0.06
    vÄĽdom
    0.06
    ,
    0.06
    /******/
    0.06
    Activations Density 0.029%

    No Known Activations