© 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 EvalsExportsinterp-engineNEWAPI 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. 81546
    Prev
    Next
    INDEX
    Explanations

    terms related to finance and financial institutions

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

    The letter "F" at the beginning of proper nouns, abbreviations like "FM," and technical terms in various contexts including academic citations, geographic names, and product references.

    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
    ires
    -0.09
    -fashioned
    -0.08
     vast
    -0.08
    istrovstvÃŃ
    -0.08
    itz
    -0.08
    leurs
    -0.08
     fiercely
    -0.07
    onse
    -0.07
     fate
    -0.07
    foundland
    -0.07
    POSITIVE LOGITS
    gerald
    0.10
    inkel
    0.10
    bruary
    0.10
    idious
    0.09
    omen
    0.08
     Fighters
    0.08
    amental
    0.08
    бол
    0.08
     Fridays
    0.08
    ivals
    0.07
    Activations Density 1.985%

    No Known Activations