© 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. 93952
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures related to quantum physics

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

    Specialized notation in mathematical physics and quantum mechanics papers, particularly SU(3) group theory notation and mathematical operations related to graph theory.

    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
    ãĥį
    -0.07
    ÑĢаж
    -0.07
     Khan
    -0.06
    sha
    -0.06
     Base
    -0.06
    oola
    -0.06
    dl
    -0.06
    avanaugh
    -0.06
     haus
    -0.06
    OCUMENT
    -0.06
    POSITIVE LOGITS
    bens
    0.06
    DonaldTrump
    0.06
    UNUSED
    0.06
    leftright
    0.06
    _compiler
    0.06
    SetColor
    0.06
    stery
    0.06
    antt
    0.06
    BUR
    0.06
    LETTE
    0.06
    Activations Density 0.823%

    No Known Activations