© 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. 11456
    Prev
    Next
    INDEX
    Explanations

    picture aspect ratio

    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
     Wer
    -0.10
    ultz
    -0.09
    Wer
    -0.09
     camer
    -0.09
    rof
    -0.09
    atrix
    -0.09
    onse
    -0.09
    endas
    -0.08
     mad
    -0.08
     Leah
    -0.08
    POSITIVE LOGITS
     aspect
    0.50
     Aspect
    0.40
    aspect
    0.40
    Aspect
    0.37
     ratio
    0.28
    _aspect
    0.27
     aspects
    0.27
    AspectRatio
    0.26
    æĸ¹éĿ¢
    0.25
    .aspect
    0.24
    Activations Density 0.060%

    No Known Activations