© 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. 76548
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to equations and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical notation from ring theory, particularly expressions involving products "aa" and invertibility notations like "R^{-1}" in the context of generalized inverses.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    itchen
    -0.08
    ¦y
    -0.07
    linger
    -0.07
    کرÛĮ
    -0.07
    Ìģt
    -0.07
    liÄŁinin
    -0.07
    OrElse
    -0.07
    ymax
    -0.07
    ｡
    -0.06
    ç¨
    -0.06
    POSITIVE LOGITS
     negative
    0.07
     minus
    0.07
     below
    0.07
     non
    0.07
     false
    0.06
     عدÙħ
    0.06
    è´Ł
    0.06
    antium
    0.06
    ipline
    0.06
     ä¸į
    0.06
    Activations Density 0.125%

    No Known Activations