© 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. 15529
    Prev
    Next
    INDEX
    Explanations

    once the

    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
    vale
    -0.11
    inox
    -0.10
    oog
    -0.10
    asıyla
    -0.09
    anton
    -0.09
     Äĩe
    -0.09
     Dare
    -0.09
     Ø®ÙĪاÙĩÙĨد
    -0.08
     ãĢĢ
    -0.08
    ç«Ł
    -0.08
    POSITIVE LOGITS
     telah
    0.18
     has
    0.18
     been
    0.16
    've
    0.16
     Äijã
    0.15
     have
    0.15
    ’;ve
    0.14
     is
    0.13
     are
    0.12
    HasBeenSet
    0.12
    Activations Density 0.027%

    No Known Activations