© 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. 62786
    Prev
    Next
    INDEX
    Explanations

    references to women in professional roles or impactful positions

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

    Headings or titles that introduce interview features, member spotlights, or profile segments in digital publications.

    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
    apon
    -0.08
     Walton
    -0.07
    inem
    -0.07
     Woj
    -0.06
    loth
    -0.06
     ><?
    -0.06
    bcc
    -0.06
     proble
    -0.06
    tir
    -0.06
     Fowler
    -0.06
    POSITIVE LOGITS
    #
    0.08
     Welcome
    0.07
    ousel
    0.07
    heet
    0.07
     onNext
    0.06
     welcome
    0.06
     interviews
    0.06
    #ac
    0.06
    heets
    0.06
    pollo
    0.06
    Activations Density 0.016%

    No Known Activations