© 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. 56778
    Prev
    Next
    INDEX
    Explanations

    german "bew" prefix

    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
    braco
    -0.10
     Sustainable
    -0.10
    maal
    -0.09
    alion
    -0.09
    dek
    -0.09
    èĽĩ
    -0.09
     Attribution
    -0.09
    row
    -0.09
    ä¼ı
    -0.09
     doom
    -0.08
    POSITIVE LOGITS
    ei
    0.11
    eg
    0.11
    ilder
    0.11
    angen
    0.10
    o
    0.10
     bew
    0.10
    een
    0.10
    driver
    0.10
    ick
    0.10
    ogen
    0.09
    Activations Density 0.013%

    No Known Activations