© 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. 17-LLAMASCOPE-RES-131K
    11. 83452
    Prev
    Next
    INDEX
    Explanations

    themes related to stigma and societal issues, particularly concerning women's health and inequality

    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
    inya
    -0.08
     pac
    -0.08
    stal
    -0.07
    ystate
    -0.07
    neh
    -0.07
    Argb
    -0.07
    utor
    -0.06
    fak
    -0.06
    ullet
    -0.06
     Kraj
    -0.06
    POSITIVE LOGITS
     society
    0.09
     treatment
    0.09
     treatments
    0.08
     Treatment
    0.07
     Treat
    0.07
     stigma
    0.07
     treating
    0.07
     discrimination
    0.07
     isolation
    0.06
     treat
    0.06
    Activations Density 0.008%

    No Known Activations