© 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. 89699
    Prev
    Next
    INDEX
    Explanations

    references to climactic moments and celebrations

    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
    antz
    -0.07
    fad
    -0.07
    reet
    -0.06
    ).__
    -0.06
     Trab
    -0.06
     Cornel
    -0.06
    .Formatting
    -0.06
    AIL
    -0.06
    íĨµ
    -0.06
    екÑĤив
    -0.06
    POSITIVE LOGITS
     cul
    0.23
    cul
    0.16
     climax
    0.15
     Cul
    0.14
     culmination
    0.14
     final
    0.13
     clim
    0.12
     finale
    0.12
     кÑĥлÑĮ
    0.11
    æľĢçµĤ
    0.11
    Activations Density 0.081%

    No Known Activations