© 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. 17-LLAMASCOPE-RES-131K
    11. 16016
    Prev
    Next
    INDEX
    Explanations

    curly braces and their usage in code structures

    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
    éŀ
    -0.07
     try
    -0.06
    ré
    -0.06
    amil
    -0.06
    esel
    -0.06
    é¥
    -0.06
    eren
    -0.06
    iler
    -0.06
    Sharper
    -0.06
     khúc
    -0.06
    POSITIVE LOGITS
    uppe
    0.06
    ONA
    0.06
    mma
    0.06
    onet
    0.06
    .sw
    0.06
    phis
    0.06
    orman
    0.06
    иÑĢа
    0.06
    atsapp
    0.06
    家çļĦ
    0.06
    Activations Density 0.005%

    No Known Activations