© 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. 10407
    Prev
    Next
    INDEX
    Explanations

    recommend or replace

    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
    Not in Any Lists

    No Comments

    Negative Logits
     reversible
    -0.11
     remorse
    -0.09
    ë£Į
    -0.09
     retract
    -0.09
     Beaut
    -0.09
     reclaimed
    -0.09
     Modified
    -0.09
    atr
    -0.08
    647
    -0.08
    uum
    -0.08
    POSITIVE LOGITS
     replacement
    0.61
     replace
    0.55
     replaced
    0.54
     Replacement
    0.52
     Replace
    0.48
     replacing
    0.47
    replace
    0.46
     replacements
    0.46
    replacement
    0.44
    Replacement
    0.44
    Activations Density 0.077%

    No Known Activations