© 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. 89669
    Prev
    Next
    INDEX
    Explanations

    significant events related to international treaties and laws

    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
    ase
    -0.06
    orp
    -0.05
     keeping
    -0.05
    ,
    -0.05
     Fleming
    -0.05
     rum
    -0.05
     Gould
    -0.05
    igs
    -0.05
     corp
    -0.05
    /
    -0.05
    POSITIVE LOGITS
    ìķ½
    0.09
    ushima
    0.09
    ÄĻk
    0.08
    stva
    0.08
    æĬŀ
    0.08
    urat
    0.08
     ký
    0.08
    Ñİк
    0.08
     ìķ½
    0.08
    ÙĪÙĬس
    0.08
    Activations Density 0.015%

    No Known Activations