© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24848
    Prev
    Next
    INDEX
    Explanations

    german compound words

    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
     Beast
    -0.11
    [sub
    -0.09
     ngh
    -0.09
    ilar
    -0.09
    ìĬ
    -0.08
    anela
    -0.08
     Hib
    -0.08
     Gilles
    -0.08
    irut
    -0.08
     vast
    -0.08
    POSITIVE LOGITS
    elter
    0.12
    nis
    0.11
    ictor
    0.10
    ert
    0.10
    entlich
    0.10
    enschaft
    0.10
    erd
    0.09
    urd
    0.09
    aeda
    0.09
     foc
    0.09
    Activations Density 0.072%

    No Known Activations