© 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. 17792
    Prev
    Next
    INDEX
    Explanations

    things and activities

    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
    ï½±
    -0.12
    ERT
    -0.11
    isko
    -0.10
    TC
    -0.08
     Anglo
    -0.08
    itel
    -0.08
     Äijá»Ŀi
    -0.08
    elve
    -0.08
    ert
    -0.08
     Trib
    -0.08
    POSITIVE LOGITS
     things
    0.56
     Things
    0.38
     thing
    0.37
    things
    0.37
    Things
    0.35
     cosas
    0.33
     веÑī
    0.28
     ways
    0.27
    thing
    0.24
     vÄĽci
    0.24
    Activations Density 0.134%

    No Known Activations