© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24796
    Prev
    Next
    INDEX
    Explanations

    follows in the style

    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
     conject
    -0.10
     belie
    -0.09
    963
    -0.09
     usur
    -0.09
    cie
    -0.09
    ｯ
    -0.09
     notions
    -0.08
     %#
    -0.08
    inks
    -0.08
    ippy
    -0.08
    POSITIVE LOGITS
     conclusion
    0.26
    Conclusion
    0.24
     ded
    0.21
     Conclusion
    0.20
     logic
    0.20
     follows
    0.20
     Ded
    0.19
     deduction
    0.19
     conclusions
    0.19
     logical
    0.19
    Activations Density 0.115%

    No Known Activations