© 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. 33727
    Prev
    Next
    INDEX
    Explanations

    ocr text or input

    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
    ency
    -0.10
     McKin
    -0.10
     wallpaper
    -0.09
    亡
    -0.09
     scrolls
    -0.09
     forest
    -0.09
     heroic
    -0.08
    erland
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
    Printing
    -0.08
    POSITIVE LOGITS
    ocr
    0.26
     OCR
    0.24
    OCR
    0.23
     Optical
    0.17
    esseract
    0.16
     recognition
    0.15
     Recognition
    0.15
     optical
    0.15
     document
    0.14
     Document
    0.14
    Activations Density 0.068%

    No Known Activations