© 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. 121584
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and associated geographic locations

    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
    subst
    -0.07
    го
    -0.07
    íĿ¥
    -0.07
     há»ĵ
    -0.06
    anko
    -0.06
    ÃŃnh
    -0.06
     Accord
    -0.06
    argo
    -0.06
     ÑģÑĥÑĤ
    -0.06
    çŃĨ
    -0.06
    POSITIVE LOGITS
     class
    0.09
     Class
    0.08
     alumni
    0.08
     gradu
    0.08
     Alumni
    0.07
     Rag
    0.07
    essen
    0.07
     graduates
    0.07
     reunion
    0.07
     graduating
    0.06
    Activations Density 0.001%

    No Known Activations