© 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. 12679
    Prev
    Next
    INDEX
    Explanations

    aid for Americans and families

    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
     disadvantaged
    -0.11
    alm
    -0.10
     Dol
    -0.10
    alth
    -0.09
     æĹ
    -0.09
    ninger
    -0.09
    aman
    -0.09
     Raised
    -0.09
     Roths
    -0.09
    ieux
    -0.09
    POSITIVE LOGITS
     low
    0.13
     families
    0.13
     unable
    0.13
     households
    0.12
     income
    0.12
     otherwise
    0.11
     vulner
    0.11
    eko
    0.11
     unins
    0.10
    amilies
    0.10
    Activations Density 0.053%

    No Known Activations