© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and stigmas surrounding women's health and reproductive rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    lio
    -0.07
    emiz
    -0.06
     Frost
    -0.06
    ÙĤدر
    -0.06
    iske
    -0.06
    oup
    -0.06
    สะ
    -0.06
    ixture
    -0.06
    .Cross
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
     associated
    0.15
    associated
    0.14
     Associated
    0.13
    Associated
    0.12
     surrounding
    0.11
     assoc
    0.11
     involved
    0.10
     aspect
    0.09
     surround
    0.09
     aspects
    0.09
    Activations Density 0.132%

    No Known Activations