© 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. 57778
    Prev
    Next
    INDEX
    Explanations

    java.util.Date or ResourceLocation.create

    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
    ManagerInterface
    -0.10
     anc
    -0.10
     Infer
    -0.09
     tort
    -0.09
    aley
    -0.09
     Brunswick
    -0.09
     Quit
    -0.08
    opper
    -0.08
    chia
    -0.08
     Rain
    -0.08
    POSITIVE LOGITS
     zone
    0.13
     Zone
    0.12
    Zone
    0.11
    iliz
    0.11
    zone
    0.11
     zones
    0.10
    delegate
    0.10
    Millis
    0.10
    ourg
    0.09
    Ë
    0.09
    Activations Density 0.012%

    No Known Activations