© 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. 80671
    Prev
    Next
    INDEX
    Explanations

    elements related to cultural identity and fashion trends

    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
     Frost
    -0.07
    Ä°stanbul
    -0.07
    marshaller
    -0.07
     patriotism
    -0.07
     Germ
    -0.07
     Newport
    -0.07
     patriot
    -0.07
    [section
    -0.07
    imei
    -0.07
    rost
    -0.07
    POSITIVE LOGITS
     Africa
    0.13
     African
    0.12
    Africa
    0.11
     tropical
    0.10
     africa
    0.10
     Africans
    0.10
     Tropical
    0.09
     jungle
    0.08
     Congo
    0.08
     malaria
    0.08
    Activations Density 0.054%

    No Known Activations