© 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. 20883
    Prev
    Next
    INDEX
    Explanations

    checking for duplicates

    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
     Compatibility
    -0.10
    åĪĩ
    -0.09
     Nob
    -0.09
    uten
    -0.09
     Dickinson
    -0.09
     uy
    -0.09
     Hyde
    -0.09
    ï¼ıï¼ı
    -0.09
    ommen
    -0.09
    Compatibility
    -0.08
    POSITIVE LOGITS
     uniqueness
    0.23
     ded
    0.21
     dup
    0.20
     Dup
    0.20
     unique
    0.19
     Unique
    0.18
    Unique
    0.16
    Dup
    0.16
     uniqu
    0.16
     DUP
    0.16
    Activations Density 0.088%

    No Known Activations