© 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. 47593
    Prev
    Next
    INDEX
    Explanations

    catch and capture

    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
     Sc
    -0.09
    iler
    -0.09
    amil
    -0.09
    Occurrences
    -0.09
     squeez
    -0.09
     squeezing
    -0.09
    cü
    -0.08
     Restricted
    -0.08
     Garn
    -0.08
    åĪ»
    -0.08
    POSITIVE LOGITS
     catch
    0.41
    catch
    0.34
     capture
    0.34
    æįķ
    0.32
    Catch
    0.31
     Catch
    0.31
     catching
    0.31
     catches
    0.30
     caught
    0.29
     catcher
    0.28
    Activations Density 0.108%

    No Known Activations