© 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. 4673
    Prev
    Next
    INDEX
    Explanations

    زÙħاÙĨ Ú©

    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
    دÙĪاج
    -0.11
     Ryder
    -0.11
    اسطة
    -0.10
     Wheeler
    -0.09
    اشÛĮÙĨ
    -0.09
     Tee
    -0.09
    ils
    -0.09
    ïºĶ
    -0.09
     Dia
    -0.09
     Ú¯ÛĮرÛĮ
    -0.09
    POSITIVE LOGITS
    .ir
    0.13
    âĢĮ
    0.13
     Dez
    0.10
     Moj
    0.10
    />č\n
    0.10
    âĢĮâĢĮ
    0.09
    724
    0.09
    åĴ¨
    0.09
     Mob
    0.09
    139
    0.09
    Activations Density 0.030%

    No Known Activations