© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43918
    Prev
    Next
    INDEX
    Explanations

    for Brazil / measure out / install J / branch of

    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
     ëķ
    -0.08
     pÅĻitom
    -0.08
    sWith
    -0.08
     latter
    -0.08
    ãĤŀ
    -0.07
    kyt
    -0.07
    égor
    -0.07
    etchup
    -0.07
    .Contracts
    -0.07
    aturdays
    -0.07
    POSITIVE LOGITS
     finally
    0.10
     also
    0.08
     Lastly
    0.08
     .
    0.08
     seemingly
    0.08
    ,
    0.07
    jos
    0.07
     AndAlso
    0.07
    .
    0.07
     even
    0.07
    Activations Density 0.037%

    No Known Activations