© 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. 38462
    Prev
    Next
    INDEX
    Explanations

    how to use or follow

    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
     input
    -0.10
     Frid
    -0.10
     Tall
    -0.09
    MSN
    -0.09
    輸
    -0.08
     vul
    -0.08
     Cure
    -0.08
     Pall
    -0.08
    WithData
    -0.08
    (internal
    -0.08
    POSITIVE LOGITS
     casting
    0.13
     code
    0.13
    代çłģ
    0.13
     cast
    0.12
    æĸ¹æ³ķ
    0.12
     method
    0.12
     código
    0.11
     calling
    0.10
     Calling
    0.10
     var
    0.10
    Activations Density 0.176%

    No Known Activations