© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    drawing conclusions

    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
    ohn
    -0.10
    chrift
    -0.09
    _keeper
    -0.09
     terminating
    -0.09
     Peb
    -0.08
    olie
    -0.08
    ï½²
    -0.08
    croll
    -0.08
    DDR
    -0.08
    cripcion
    -0.08
    POSITIVE LOGITS
     draw
    0.41
     conclusions
    0.40
     conclusion
    0.38
     drawn
    0.36
     drew
    0.34
     Draw
    0.34
     draws
    0.34
    Conclusion
    0.34
     drawing
    0.34
    draw
    0.32
    Activations Density 0.121%

    No Known Activations