© 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. 63051
    Prev
    Next
    INDEX
    Explanations

    data related to age and demographic statistics

    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
    peech
    -0.07
    ense
    -0.07
    jev
    -0.07
    roit
    -0.07
    ÄŁinden
    -0.07
    juana
    -0.07
    èį
    -0.06
    ictim
    -0.06
     despre
    -0.06
    hive
    -0.06
    POSITIVE LOGITS
     Elder
    0.09
     elder
    0.08
     elderly
    0.07
     senior
    0.07
     seniors
    0.07
    eyer
    0.07
     Senior
    0.07
     elders
    0.07
    VERT
    0.07
     geri
    0.06
    Activations Density 0.002%

    No Known Activations