© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53737
    Prev
    Next
    INDEX
    Explanations

    mentions of various occupations and roles related to caregiving or service

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Words referring to service workers and subordinate occupational roles, particularly in institutional or commercial contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    人çī©
    -0.08
    arkin
    -0.08
     addCriterion
    -0.07
    hlen
    -0.07
    openh
    -0.07
    lero
    -0.07
    /preferences
    -0.07
    raki
    -0.07
    illez
    -0.07
    tro
    -0.07
    POSITIVE LOGITS
     whom
    0.08
     who
    0.07
    ship
    0.07
    who
    0.07
    rix
    0.07
     cum
    0.07
    age
    0.06
    ess
    0.06
    uels
    0.06
    /helper
    0.06
    Activations Density 0.051%

    No Known Activations