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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 829
    Prev
    Next
    INDEX
    Explanations

    Please execute instruction

    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
     prop
    -0.10
    hoff
    -0.09
    844
    -0.09
    igate
    -0.09
    _IMPL
    -0.09
    ToProps
    -0.08
     foc
    -0.08
    ï¼ıï¼ı
    -0.08
     Crew
    -0.08
     pres
    -0.08
    POSITIVE LOGITS
     finish
    0.11
     completion
    0.11
     finishing
    0.10
     instruct
    0.09
    注æĦı
    0.09
     completes
    0.09
    åIJĪ
    0.09
     storyt
    0.09
    Finish
    0.09
     echo
    0.09
    Activations Density 0.016%

    No Known Activations