© 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. 75913
    Prev
    Next
    INDEX
    Explanations

    numeric values and symbols related to financial or mathematical concepts

    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
    unate
    -0.08
    uga
    -0.07
    alah
    -0.07
    eten
    -0.07
    iyim
    -0.07
    es
    -0.06
    (strtolower
    -0.06
    ãģªãģĮ
    -0.06
    ETA
    -0.06
    rious
    -0.06
    POSITIVE LOGITS
     this
    0.09
     This
    0.08
     ie
    0.07
    this
    0.07
     ìĿ´ëĬĶ
    0.07
     or
    0.07
    This
    0.07
    è¿Ļ个
    0.07
     ÑįÑĤо
    0.07
    ucher
    0.07
    Activations Density 0.069%

    No Known Activations