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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89663
    Prev
    Next
    INDEX
    Explanations

    mentions of talent or references to talented individuals within various contexts

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

    The word "talent" refers to skilled individuals or special abilities in various contexts such as entertainment, workforce, recruitment, competitions, or performances. Often appears in professional descriptions, event listings, or biographical information.

    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
    illon
    -0.08
    sdale
    -0.08
    ordin
    -0.08
    jang
    -0.08
    oble
    -0.07
    cliffe
    -0.07
    fty
    -0.07
    oker
    -0.07
    leston
    -0.07
    ople
    -0.07
    POSITIVE LOGITS
    ocracy
    0.07
    vise
    0.06
    mos
    0.06
    fully
    0.06
    ké
    0.06
    ted
    0.06
    itudes
    0.06
    à¸ĩาà¸Ļ
    0.06
    ific
    0.06
    uous
    0.06
    Activations Density 0.010%

    No Known Activations