© 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. 46006
    Prev
    Next
    INDEX
    Explanations

    is does are questions

    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
    uzzi
    -0.10
     wag
    -0.09
    ceipt
    -0.09
     hat
    -0.09
     bub
    -0.09
    hen
    -0.08
    .SDK
    -0.08
    ercul
    -0.08
     ank
    -0.08
    omu
    -0.08
    POSITIVE LOGITS
    lington
    0.11
    chem
    0.11
    bn
    0.10
    (es
    0.10
     Wass
    0.09
    olation
    0.09
    mail
    0.09
     ли
    0.09
    BBBB
    0.09
    lam
    0.08
    Activations Density 0.017%

    No Known Activations