© 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. 91584
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and economic data related to employment

    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
    ç©
    -0.08
    aç
    -0.08
     hete
    -0.07
    δη
    -0.07
    iyas
    -0.07
    errat
    -0.07
     lesbi
    -0.07
     kli
    -0.07
    .same
    -0.07
     mặt
    -0.07
    POSITIVE LOGITS
     Fare
    0.07
     Least
    0.07
     tops
    0.07
     بÛĮØ´
    0.07
     least
    0.06
     rank
    0.06
     hardest
    0.06
     among
    0.06
    least
    0.06
    apol
    0.06
    Activations Density 0.050%

    No Known Activations