© 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. 37459
    Prev
    Next
    INDEX
    Explanations

    percentage values

    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
     %-
    -0.12
    ãĤ¡
    -0.09
     Blanco
    -0.09
    %/
    -0.09
    dG
    -0.09
    figcaption
    -0.09
    (æĹ¥
    -0.09
     hott
    -0.09
    egal
    -0.09
     certif
    -0.09
    POSITIVE LOGITS
    /weather
    0.08
     Moff
    0.08
     ï¼
    0.08
     Mitchell
    0.08
    iot
    0.08
    िशत
    0.08
     Curtis
    0.08
    ÂŃ
    0.08
    ady
    0.08
     closely
    0.08
    Activations Density 0.036%

    No Known Activations