© 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. 18194
    Prev
    Next
    INDEX
    Explanations

    poverty, corruption, violence, delinquency

    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
     gust
    -0.09
     lif
    -0.09
     cryst
    -0.09
    Animating
    -0.09
    zee
    -0.09
    imest
    -0.09
    MDB
    -0.08
     Haz
    -0.08
     Appeals
    -0.08
    iolet
    -0.08
    POSITIVE LOGITS
     suburban
    0.12
     mortal
    0.11
    crease
    0.10
     poverty
    0.10
     frag
    0.10
     Sho
    0.09
     cinematic
    0.09
    onda
    0.09
     crisis
    0.09
     Pir
    0.09
    Activations Density 0.169%

    No Known Activations