© 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. 38474
    Prev
    Next
    INDEX
    Explanations

    descriptors of social and racial dynamics

    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
    ainter
    -0.07
    azer
    -0.06
    -ÑĤо
    -0.06
     Tits
    -0.06
     Amerik
    -0.06
    ака
    -0.06
    Å
    -0.06
    ainting
    -0.06
    AllWindows
    -0.06
     Saunders
    -0.06
    POSITIVE LOGITS
     either
    0.07
    edImage
    0.07
     stereotype
    0.07
    LOSE
    0.07
     stere
    0.07
    either
    0.07
    ãĥ©ãĤ¹
    0.06
     scene
    0.06
     necessarily
    0.06
     ster
    0.06
    Activations Density 0.032%

    No Known Activations