© 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. 75887
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to various types of equipment, production, and business terminology

    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
    findViewById
    -0.07
     Kür
    -0.07
    بÛĮÙĨÛĮ
    -0.07
     yacc
    -0.07
    osta
    -0.07
    /Instruction
    -0.06
     ÄĮer
    -0.06
    fillType
    -0.06
    asant
    -0.06
    anship
    -0.06
    POSITIVE LOGITS
     equally
    0.07
    âĢ¦↵↵↵
    0.07
    dit
    0.06
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.06
    亦
    0.06
    âĢļ
    0.06
     likewise
    0.06
     sức
    0.05
    .$.
    0.05
     naopak
    0.05
    Activations Density 0.200%

    No Known Activations