© 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. 46084
    Prev
    Next
    INDEX
    Explanations

    extracting medical terms from UMLS

    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
     Bom
    -0.09
     Ùħعت
    -0.09
     Fro
    -0.09
    antan
    -0.09
     Kerr
    -0.08
     breadcrumbs
    -0.08
    zk
    -0.08
     wom
    -0.08
    &e
    -0.08
    Template
    -0.08
    POSITIVE LOGITS
    .nlm
    0.23
     Pub
    0.21
    .nih
    0.18
     Med
    0.18
     pub
    0.17
     PUB
    0.17
     Mesh
    0.16
    Pub
    0.16
     NC
    0.15
     MED
    0.15
    Activations Density 0.039%

    No Known Activations