© 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. 92270
    Prev
    Next
    INDEX
    Explanations

    numerical information and time references related to events or artworks

    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
    .baidu
    -0.07
    pressor
    -0.06
    upd
    -0.06
    áy
    -0.06
    iran
    -0.06
    ла
    -0.06
     زد
    -0.06
    inned
    -0.06
    ucer
    -0.06
    lemn
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.10
    rez
    0.07
    razier
    0.07
    olle
    0.07
    mts
    0.06
    ç²Ĵ
    0.06
    -webpack
    0.06
    chwitz
    0.06
    аниÑĨ
    0.06
     lect
    0.06
    Activations Density 0.001%

    No Known Activations