© 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. 53302
    Prev
    Next
    INDEX
    Explanations

    catalyst and its properties

    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
     Fame
    -0.09
     mug
    -0.09
    æ¨
    -0.08
     ÙĤر
    -0.08
    ::~
    -0.08
    .foundation
    -0.08
     Verfügung
    -0.08
     TARGET
    -0.08
     ore
    -0.08
    urret
    -0.08
    POSITIVE LOGITS
     catalyst
    0.26
     Catalyst
    0.23
     catal
    0.22
    åĤ¬
    0.20
     Catal
    0.19
    atal
    0.16
    ATAL
    0.13
     xúc
    0.13
     Catalonia
    0.12
     cata
    0.12
    Activations Density 0.037%

    No Known Activations