© 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. 117320
    Prev
    Next
    INDEX
    Explanations

    empty space or whitespace characters 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
     Tray
    -0.07
    elf
    -0.07
    449
    -0.07
    ìĤ¼
    -0.06
    amon
    -0.06
     getopt
    -0.06
    ather
    -0.06
    ILER
    -0.06
    ej
    -0.06
    umat
    -0.06
    POSITIVE LOGITS
    erval
    0.06
    holder
    0.06
    cko
    0.06
    cles
    0.06
    ghest
    0.06
    ierge
    0.06
    lcd
    0.06
    ovny
    0.06
    erton
    0.06
    eso
    0.06
    Activations Density 0.020%

    No Known Activations