© 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. 38507
    Prev
    Next
    INDEX
    Explanations

    properly configured or added

    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
     Laurent
    -0.10
    575
    -0.09
     âŁ
    -0.09
     compreh
    -0.09
    anal
    -0.09
     Berk
    -0.08
     Rex
    -0.08
     Sylv
    -0.08
    addon
    -0.08
    zen
    -0.08
    POSITIVE LOGITS
     correct
    0.24
     spell
    0.24
     spelling
    0.23
    æŃ£ç¡®
    0.22
     spelled
    0.21
     correctly
    0.19
    spell
    0.19
     Spell
    0.19
     пÑĢавилÑĮно
    0.18
     spells
    0.18
    Activations Density 0.045%

    No Known Activations