© 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. 34280
    Prev
    Next
    INDEX
    Explanations

    certain clinical 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
     Sov
    -0.09
    vl
    -0.09
    emoth
    -0.09
    indsight
    -0.09
    çĹĩ
    -0.09
    InMillis
    -0.08
    557
    -0.08
    ä¸
    -0.08
    _patient
    -0.08
    Dyn
    -0.08
    POSITIVE LOGITS
     underlying
    0.29
     existing
    0.23
     history
    0.22
    -existing
    0.20
    existing
    0.18
     com
    0.18
     conditions
    0.18
     Existing
    0.18
    history
    0.17
     chronic
    0.17
    Activations Density 0.048%

    No Known Activations