© 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. 72640
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to user interface design in programming

    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
    ervoir
    -0.06
    istrov
    -0.06
    iane
    -0.06
    hiba
    -0.06
    rf
    -0.06
    urge
    -0.06
    torrent
    -0.06
     Bilg
    -0.06
    hab
    -0.06
     mour
    -0.06
    POSITIVE LOGITS
    otle
    0.06
     ìĥģëĮĢ
    0.06
    ungs
    0.06
    alles
    0.06
    ãi
    0.06
     |↵
    0.06
    amt
    0.06
    uner
    0.06
    unga
    0.05
    .spacing
    0.05
    Activations Density 0.001%

    No Known Activations