© 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. 53231
    Prev
    Next
    INDEX
    Explanations

    then followed by comma

    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
     now
    -0.10
    ues
    -0.09
    woke
    -0.09
    ted
    -0.09
     поба
    -0.09
    ses
    -0.08
    anno
    -0.08
    .Formatter
    -0.08
    ges
    -0.08
    ividual
    -0.08
    POSITIVE LOGITS
    umber
    0.18
    ews
    0.13
    ew
    0.13
    æīį
    0.13
     comes
    0.13
    hin
    0.13
    -ÑĤо
    0.12
    ormal
    0.12
    åij¢
    0.12
    -current
    0.11
    Activations Density 0.026%

    No Known Activations