© 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 EvalsExportsAPI 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. 85632
    Prev
    Next
    INDEX
    Explanations

    specialized notation or symbols in scientific data

    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
    teri
    -0.08
    stown
    -0.08
    978
    -0.07
    rapped
    -0.07
    iaux
    -0.07
    .va
    -0.07
    ган
    -0.07
    eyer
    -0.07
    ighton
    -0.07
    stuff
    -0.07
    POSITIVE LOGITS
     odd
    0.06
    ansa
    0.06
    FUN
    0.06
    abela
    0.06
    ppy
    0.06
    emu
    0.06
     curt
    0.05
     assignable
    0.05
     Weinstein
    0.05
    ,
    0.05
    Activations Density 0.058%

    No Known Activations