© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64748
    Prev
    Next
    INDEX
    Explanations

    deep blue green

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     coloured
    -0.15
     crimson
    -0.14
     colourful
    -0.14
     colored
    -0.13
     colorful
    -0.13
     turquoise
    -0.13
     Crimson
    -0.13
     Colour
    -0.12
     rainbow
    -0.11
     Rainbow
    -0.11
    POSITIVE LOGITS
     green
    0.26
     blue
    0.25
     red
    0.21
     burg
    0.19
     mag
    0.19
     Burg
    0.17
     Green
    0.17
     deep
    0.16
     royal
    0.16
    blue
    0.16
    Activations Density 0.147%

    No Known Activations