© 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. 38342
    Prev
    Next
    INDEX
    Explanations

    outlining steps and topics

    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
     details
    -0.13
     detail
    -0.11
     specifics
    -0.11
     detal
    -0.11
    Details
    -0.10
     particulars
    -0.10
     detalles
    -0.10
    _details
    -0.10
    ogan
    -0.10
     Details
    -0.10
    POSITIVE LOGITS
     major
    0.15
     steps
    0.14
     key
    0.13
     sal
    0.13
     entire
    0.12
     contents
    0.11
     Entire
    0.11
    steps
    0.11
     types
    0.11
     main
    0.11
    Activations Density 0.099%

    No Known Activations