© 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. 20455
    Prev
    Next
    INDEX
    Explanations

    conditional or alternative phrasing

    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
     [âĢ¦
    -0.09
    ãĥ¼ãĥ¼
    -0.09
    ï½ŀï½ŀ
    -0.09
     %[
    -0.08
    ãĢģãĢģ
    -0.08
    âĢIJ
    -0.07
    raph
    -0.07
     may
    -0.07
     Sous
    -0.07
    ched
    -0.06
    POSITIVE LOGITS
    <|begin_of_text|>
    0.10
    EMPLARY
    0.09
    ******č\n
    0.09
     ìĿ¸ê¸°ê¸Ģ
    0.08
    ¡°
    0.08
    ÐĿÐĨ
    0.08
    Âģ@
    0.08
    %č\n
    0.08
    .Formatter
    0.08
    ¨ë¶Ģ
    0.07
    Activations Density 3.539%

    No Known Activations