© 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. 47388
    Prev
    Next
    INDEX
    Explanations

    and that people can change

    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
    StateManager
    -0.09
     FUCK
    -0.09
     fuck
    -0.08
     ong
    -0.08
     uniquely
    -0.08
    stra
    -0.08
    rophe
    -0.08
     fucking
    -0.07
     DVDs
    -0.07
     immediately
    -0.07
    POSITIVE LOGITS
    flen
    0.09
     VÅ¡ech
    0.09
     (*((
    0.08
    ismet
    0.08
    Routine
    0.08
     ilma
    0.08
     xhttp
    0.07
     isten
    0.07
    ÃĹ\n\n
    0.07
    ｯ
    0.07
    Activations Density 0.012%

    No Known Activations