© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    mental health and substance abuse

    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
     cough
    -0.13
     unconscious
    -0.11
     sore
    -0.10
    astes
    -0.10
    ussy
    -0.10
     Bau
    -0.09
     AIDS
    -0.09
     decre
    -0.09
     blindness
    -0.09
     dysfunction
    -0.09
    POSITIVE LOGITS
     mental
    0.45
     Mental
    0.38
    mental
    0.35
    ental
    0.22
    ç²¾ç¥ŀ
    0.20
     depression
    0.20
     mentally
    0.19
     stigma
    0.18
     MH
    0.17
    æĬij
    0.17
    Activations Density 0.131%

    No Known Activations