© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 15658
    Prev
    Next
    INDEX
    Explanations

    myelitis, neuritis, sclerosis, sepsis, otitis

    np_acts-logits-general · gemini-2.5-flash-lite

    medical terminology, particularly disease names and conditions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ndx
    -0.11
     Bryce
    -0.09
     Sentry
    -0.09
     abnormal
    -0.09
     ZIP
    -0.08
     Dix
    -0.08
     allerg
    -0.08
    805
    -0.08
     Diagnosis
    -0.08
    normalized
    -0.08
    POSITIVE LOGITS
     syndrome
    0.17
    erosis
    0.13
    itis
    0.13
     Syndrome
    0.13
    oriasis
    0.13
    综åIJĪ
    0.12
    atitis
    0.12
    rosis
    0.12
    opathy
    0.12
     dyst
    0.11
    Activations Density 0.127%

    No Known Activations