© 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. 63718
    Prev
    Next
    INDEX
    Explanations

    smile and related sentiment

    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
    •Smiley Face Features
    •1. Smiley face List
    •3. Worry face
    •4. Confused face
    •5. Sleepy face
    •6. Frog face
    •7. Bear face
    •8. Panda face
    •9. Pig face
    •10. Cow face
    •11. Smile edited to frown
    •12. Eye size edited
    •13. Changing Order
    •14. Changing eyes to squares
    •15. Changing mouth first

    No Comments

    Negative Logits
    ï¾ŀ
    -0.10
     hilarious
    -0.10
     Kai
    -0.09
     sly
    -0.09
     hilar
    -0.09
    ilar
    -0.09
    oggler
    -0.09
     infl
    -0.09
     glu
    -0.08
    /of
    -0.08
    POSITIVE LOGITS
     smile
    0.37
     smiled
    0.30
     Smile
    0.29
     smiles
    0.29
     ÑĥлÑĭб
    0.27
     grin
    0.20
    å¾®ç¬ij
    0.20
     smiling
    0.18
     broad
    0.17
     grinned
    0.16
    Activations Density 0.063%

    No Known Activations