© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90180
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and formatting

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

    Characters that serve as mathematical notation symbols (like subscripts, superscripts) or punctuation at sentence boundaries (especially question marks before line breaks).

    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
     Щ
    -0.06
    Mill
    -0.06
    arges
    -0.06
     ÙħتØŃ
    -0.06
    riel
    -0.06
    yd
    -0.06
    æĮ
    -0.06
    wind
    -0.06
    crc
    -0.06
    Threshold
    -0.06
    POSITIVE LOGITS
     diam
    0.06
    vÃŃce
    0.06
     spoj
    0.06
    QtCore
    0.06
     Vir
    0.06
    kad
    0.06
    hoe
    0.06
    :params
    0.06
    ãĥªãĤ«
    0.06
    connexion
    0.06
    Activations Density 0.007%

    No Known Activations