© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82918
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic and financial terms

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

    Technical terms or proper nouns in different languages, often representing technology standards (CSS, HTML, SVG), programming terms, company/product names (NASDAQ), organizations (Exchange), or educational institutions (School, College) with their original non-English spelling maintained.

    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
    elo
    -0.07
     zda
    -0.07
    emek
    -0.06
    taÅŁ
    -0.06
    /misc
    -0.06
    reon
    -0.06
     Heller
    -0.06
    ayo
    -0.06
     clearing
    -0.06
    ayi
    -0.06
    POSITIVE LOGITS
     authDomain
    0.07
    pread
    0.07
     asses
    0.06
    anova
    0.06
    chin
    0.06
    cade
    0.06
    leton
    0.06
    cale
    0.06
     humble
    0.06
    :///
    0.06
    Activations Density 0.114%

    No Known Activations