© 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. 123699
    Prev
    Next
    INDEX
    Explanations

    keywords related to web functionality and user interaction

    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
    vr
    -0.06
    æİĪ
    -0.06
     Cumberland
    -0.06
    appa
    -0.06
    engers
    -0.06
     Bình
    -0.06
    ant
    -0.06
    ouch
    -0.06
    ollo
    -0.05
    TON
    -0.05
    POSITIVE LOGITS
    CESS
    0.08
    zym
    0.07
    .updateDynamic
    0.07
     फल
    0.07
     abych
    0.07
    <decltype
    0.07
    лаÑĤи
    0.07
    ĵåIJį
    0.06
    аÑĢÑĩ
    0.06
    vetica
    0.06
    Activations Density 0.001%

    No Known Activations