© 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. 20631
    Prev
    Next
    INDEX
    Explanations

    he would/hätte

    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
     Hav
    -0.11
    udur
    -0.09
    ừ
    -0.09
     Hearth
    -0.09
     Robbins
    -0.09
    ernen
    -0.08
    \n
    -0.08
     HAS
    -0.08
    HAS
    -0.08
     future
    -0.08
    POSITIVE LOGITS
     hätte
    0.28
     would
    0.28
     wouldn
    0.25
    would
    0.24
     Would
    0.24
    Would
    0.24
     бÑĭ
    0.24
     hät
    0.20
     wäre
    0.18
     Wouldn
    0.17
    Activations Density 0.073%

    No Known Activations