© 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. 27035
    Prev
    Next
    INDEX
    Explanations

    geographic locations specifically related to Australia and its localities

    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
    uye
    -0.08
    InnerHTML
    -0.08
    onya
    -0.07
    .Contracts
    -0.07
    aec
    -0.07
    nom
    -0.07
    ãİ
    -0.07
    _nom
    -0.07
    ucci
    -0.07
    rire
    -0.07
    POSITIVE LOGITS
     ourselves
    0.08
     shores
    0.06
    aks
    0.06
     drag
    0.06
     our
    0.06
     ours
    0.06
     too
    0.06
     ones
    0.06
     and
    0.05
     import
    0.05
    Activations Density 0.097%

    No Known Activations