© 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. 53385
    Prev
    Next
    INDEX
    Explanations

    conditions for reasons

    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
    endregion
    -0.10
     pÅĻÃŃpadnÄĽ
    -0.09
     بÙĪابة
    -0.09
    urch
    -0.09
    uo
    -0.08
    Mixin
    -0.08
     ÑĤоже
    -0.08
    yy
    -0.08
    abad
    -0.08
     Rounded
    -0.08
    POSITIVE LOGITS
     because
    0.18
     поÑĤомÑĥ
    0.15
    because
    0.13
     porque
    0.12
     à¤ĩसल
    0.11
    åĽłä¸º
    0.10
     omdat
    0.10
     karena
    0.10
    ë¿IJ
    0.10
    å¦Ĥä¸ĭ
    0.10
    Activations Density 0.301%

    No Known Activations