© 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. 42542
    Prev
    Next
    INDEX
    Explanations

    references to governmental or municipal resolutions and measures

    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
     Appalachian
    -0.07
     Newfoundland
    -0.07
     Appalach
    -0.07
    Miami
    -0.07
     Bahamas
    -0.06
     Yankees
    -0.06
     Philly
    -0.06
     Hurricanes
    -0.06
     tornado
    -0.06
    abin
    -0.06
    POSITIVE LOGITS
     California
    0.25
     Californ
    0.23
    California
    0.23
     california
    0.20
     Calif
    0.19
     Sacramento
    0.18
     Fresno
    0.18
     Los
    0.17
    ifornia
    0.16
     UCLA
    0.16
    Activations Density 1.217%

    No Known Activations