© 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. 58620
    Prev
    Next
    INDEX
    Explanations

    X is Y descriptions

    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
     numerous
    -0.09
    tring
    -0.09
    éĤ£éĩĮ
    -0.09
    forth
    -0.08
    udy
    -0.08
    inium
    -0.08
    /apis
    -0.08
     termed
    -0.08
    ief
    -0.08
    792
    -0.08
    POSITIVE LOGITS
     unusual
    0.12
     also
    0.12
     unique
    0.11
    omers
    0.11
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.11
     ​​
    0.11
    _unique
    0.10
     Sto
    0.10
    also
    0.10
     particularly
    0.09
    Activations Density 0.089%

    No Known Activations