© 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. 18080
    Prev
    Next
    INDEX
    Explanations

    how to do something

    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
    zel
    -0.10
     quale
    -0.09
    ibal
    -0.09
    wick
    -0.08
    upt
    -0.08
     shri
    -0.08
    819
    -0.08
    WHAT
    -0.08
     quali
    -0.08
    (
    -0.08
    POSITIVE LOGITS
     how
    0.61
    å¦Ĥä½ķ
    0.48
    how
    0.44
     cómo
    0.42
     How
    0.42
    How
    0.37
     nasıl
    0.37
     ÚĨÚ¯ÙĪÙĨÙĩ
    0.37
     HOW
    0.34
     ìĸ´ëĸ»ê²Į
    0.34
    Activations Density 0.296%

    No Known Activations