© 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. 15210
    Prev
    Next
    INDEX
    Explanations

    instances of academic journals and citations

    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
     lite
    -0.07
     thú
    -0.06
    à¥įड
    -0.06
    thin
    -0.06
    Vect
    -0.06
    unos
    -0.06
    ãģ¨ãĤĤ
    -0.06
     herd
    -0.06
    .Exec
    -0.06
    Ïį
    -0.05
    POSITIVE LOGITS
    enville
    0.07
     TMPro
    0.07
    flater
    0.06
    istrovstvÃŃ
    0.06
     showc
    0.06
    hya
    0.06
    inox
    0.06
    нин
    0.06
    asco
    0.06
    yonel
    0.06
    Activations Density 0.002%

    No Known Activations