© 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. 60569
    Prev
    Next
    INDEX
    Explanations

    symptoms and conditions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     pathological
    -0.12
     Sinclair
    -0.09
    azu
    -0.09
     infectious
    -0.09
     debilitating
    -0.09
     sclerosis
    -0.09
     Coch
    -0.08
    ength
    -0.08
     parts
    -0.08
     trans
    -0.08
    POSITIVE LOGITS
     condition
    0.42
    condition
    0.31
     Condition
    0.31
     disease
    0.28
    Condition
    0.27
     symptoms
    0.24
     CONDITION
    0.23
    (condition
    0.21
    _condition
    0.21
    .condition
    0.20
    Activations Density 0.060%

    No Known Activations