© 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. 1333
    Prev
    Next
    INDEX
    Explanations

    language related to inclusivity and equal opportunity in an employment context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ammen
    -0.07
    isko
    -0.06
    âĢİ
    -0.06
     presup
    -0.06
     estud
    -0.06
     knock
    -0.06
     mortgages
    -0.05
     readiness
    -0.05
     drop
    -0.05
    neys
    -0.05
    POSITIVE LOGITS
     Equal
    0.08
     equal
    0.08
    Equal
    0.08
    #__
    0.07
    Neutral
    0.07
    (Equal
    0.07
     Goods
    0.07
    ãĥ¼ãĥĨ
    0.07
    neutral
    0.07
    jang
    0.07
    Activations Density 0.004%

    No Known Activations