© 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. 127494
    Prev
    Next
    INDEX
    Explanations

    elements related to table formatting in coding

    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
    hood
    -0.07
    è¾ŀ
    -0.06
    earing
    -0.06
     Warehouse
    -0.06
    کات
    -0.06
    ë°Ģ
    -0.06
    urve
    -0.06
     Woodward
    -0.05
     gal
    -0.05
    asto
    -0.05
    POSITIVE LOGITS
     cellpadding
    0.08
    -layout
    0.08
     spreads
    0.07
    <tbody
    0.07
     spread
    0.07
    oje
    0.07
    orz
    0.07
     table
    0.07
    ør
    0.07
     Spread
    0.07
    Activations Density 0.005%

    No Known Activations