© 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. 58312
    Prev
    Next
    INDEX
    Explanations

    references to television programming and media previews

    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
     Grass
    -0.06
    dust
    -0.06
    fty
    -0.06
    (PR
    -0.06
    loom
    -0.06
    -ÑĤаки
    -0.06
    _UNIQUE
    -0.06
     Og
    -0.05
    arena
    -0.05
     详æĥħ
    -0.05
    POSITIVE LOGITS
    Sortable
    0.07
    QUI
    0.07
    'gc
    0.07
    imary
    0.07
    fragistics
    0.07
    umper
    0.06
    prung
    0.06
    stro
    0.06
    kea
    0.06
    imdi
    0.06
    Activations Density 0.026%

    No Known Activations