© 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. 15-LLAMASCOPE-RES-131K
    11. 86436
    Prev
    Next
    INDEX
    Explanations

    references to technology-related items and their specifications or uses

    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
    vox
    -0.07
     Rover
    -0.06
    brush
    -0.06
     sm
    -0.06
    emme
    -0.06
    wig
    -0.06
     Que
    -0.06
    bur
    -0.06
    Msp
    -0.06
    793
    -0.06
    POSITIVE LOGITS
    EY
    0.07
    Transformer
    0.06
     Eye
    0.06
     monitor
    0.06
    tractor
    0.06
    rav
    0.06
    íĺij
    0.06
    Ÿ
    0.06
    à¸ķา
    0.06
    cko
    0.06
    Activations Density 0.003%

    No Known Activations