© 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. 19414
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, and comparisons

    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
    ĵĺ
    -0.10
     Scot
    -0.10
     Weston
    -0.09
    ixel
    -0.09
    SearchParams
    -0.08
     Eck
    -0.08
    COPE
    -0.08
    cep
    -0.08
    131
    -0.08
    .Companion
    -0.08
    POSITIVE LOGITS
     âĨĺ
    0.12
     smaller
    0.12
     Belmont
    0.10
    ending
    0.09
     shorter
    0.09
     lower
    0.09
    amb
    0.09
     impro
    0.09
    avig
    0.09
     Pays
    0.09
    Activations Density 0.102%

    No Known Activations