© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 61342
    Prev
    Next
    INDEX
    Explanations

    attributes related to dimensions and layout in styling or HTML contexts

    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
    .jasper
    -0.06
    loi
    -0.06
    ead
    -0.06
     je
    -0.06
     Spend
    -0.06
    izzo
    -0.06
    stras
    -0.06
    arious
    -0.06
     Bates
    -0.06
    761
    -0.06
    POSITIVE LOGITS
    ÙħÙĦØ©
    0.06
    941
    0.06
    ìĦł
    0.06
    emez
    0.06
     ÐIJнд
    0.06
     Noel
    0.06
     cracking
    0.06
    .datab
    0.06
    oon
    0.06
     ==============================================================
    0.05
    Activations Density 0.001%

    No Known Activations