© 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. 34875
    Prev
    Next
    INDEX
    Explanations

    concepts and technical domains

    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
    776
    -0.12
    raf
    -0.11
     surrounding
    -0.10
    gh
    -0.09
    elf
    -0.09
    illo
    -0.09
     Vend
    -0.09
    632
    -0.09
    214
    -0.09
     mem
    -0.09
    POSITIVE LOGITS
     Ú©Ùĩ
    0.13
     that
    0.12
     ÏĢοÏħ
    0.11
     коÑĤоÑĢÑĥÑİ
    0.11
     kterou
    0.11
     hogy
    0.11
     which
    0.11
     mÃł
    0.10
     että
    0.10
    ázev
    0.10
    Activations Density 0.262%

    No Known Activations