© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36004
    Prev
    Next
    INDEX
    Explanations

    earn law, ship yards, explicit sexual

    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
     urlpatterns
    -0.09
    dictions
    -0.08
    .Repositories
    -0.08
    .synthetic
    -0.08
    FormItem
    -0.08
    WARDED
    -0.07
    ê°¤
    -0.07
    'options
    -0.07
     prere
    -0.07
    AttributeName
    -0.07
    POSITIVE LOGITS
     \$
    0.08
    oucher
    0.07
    446
    0.07
     xxxx
    0.07
     $.
    0.07
    ioned
    0.07
     commissioned
    0.07
    loc
    0.07
    ÃĹ\n\n
    0.07
     compass
    0.07
    Activations Density 0.056%

    No Known Activations