© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 4775
    Prev
    Next
    INDEX
    Explanations

    classical physics and macro

    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
     dise
    -0.09
     tượng
    -0.09
     unus
    -0.09
     thin
    -0.09
     Thorn
    -0.09
     Hick
    -0.08
    Ïģη
    -0.08
     èIJ
    -0.08
     unread
    -0.08
     Clips
    -0.08
    POSITIVE LOGITS
     classical
    0.29
     macro
    0.24
     Classical
    0.24
     Macro
    0.19
    Macro
    0.19
     Newton
    0.18
    macro
    0.17
    Newton
    0.16
     macros
    0.15
    å®ı
    0.15
    Activations Density 0.086%

    No Known Activations