© 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. 10568
    Prev
    Next
    INDEX
    Explanations

    M followed by ens{

    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
     provid
    -0.11
     Donovan
    -0.10
    /
    -0.09
    EDA
    -0.09
     Hir
    -0.09
     Kemp
    -0.09
     capped
    -0.08
     arch
    -0.08
     sortBy
    -0.08
     tumble
    -0.08
    POSITIVE LOGITS
    charAt
    0.10
    Computed
    0.10
     fark
    0.09
    err
    0.09
    Hat
    0.09
     addCriterion
    0.09
    enumerator
    0.09
    à¸ī
    0.09
    .scalablytyped
    0.08
     tvb
    0.08
    Activations Density 0.094%

    No Known Activations