© 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. 14232
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and events

    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
    olang
    -0.08
    ÙĬدة
    -0.07
    енка
    -0.07
    edido
    -0.06
     modern
    -0.06
     protected
    -0.06
     incoming
    -0.06
     foreign
    -0.06
     rac
    -0.06
     Modern
    -0.06
    POSITIVE LOGITS
    onds
    0.08
    úp
    0.07
    tvrt
    0.06
     Mate
    0.06
     comeback
    0.06
    ÑĤоÑĢ
    0.06
    Verts
    0.06
    åģ¥
    0.06
    vla
    0.06
    agal
    0.06
    Activations Density 0.015%

    No Known Activations