© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 10748
    Prev
    Next
    INDEX
    Explanations

    e-commerce, e-books, e-mail

    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
    Negative Logits
    lec
    -0.13
    lixir
    -0.13
    levator
    -0.12
    lectric
    -0.11
    cole
    -0.11
    lem
    -0.10
    lect
    -0.10
    urovision
    -0.10
    ver
    -0.10
    conomics
    -0.10
    POSITIVE LOGITS
    .g
    0.16
     e
    0.13
    aves
    0.13
    ero
    0.12
    aque
    0.12
    .preventDefault
    0.12
     ven
    0.12
     commerce
    0.12
    pon
    0.11
    ases
    0.11
    Activations Density 0.044%

    No Known Activations