© 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. 108865
    Prev
    Next
    INDEX
    Explanations

    discussions related to international relations and geopolitical alliances

    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
     uranus
    -0.07
    UBY
    -0.06
    ãĥ¼ãĤ¸
    -0.06
    ialias
    -0.06
    bourg
    -0.06
    ÏĨÏħ
    -0.06
    ÙĨدر
    -0.06
     '.
    -0.06
    fak
    -0.06
     ê³Ħ
    -0.06
    POSITIVE LOGITS
    анк
    0.09
     Intervention
    0.08
     Western
    0.08
    欧ç¾İ
    0.08
     EU
    0.08
     United
    0.08
     intervention
    0.08
     external
    0.07
    EU
    0.07
     foreign
    0.07
    Activations Density 0.086%

    No Known Activations