© 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. 17062
    Prev
    Next
    INDEX
    Explanations

    founding fathers, charts, decades, debate, company, California, branch, world, sexuality

    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
    пÑĢимеÑĢ
    -0.10
    anela
    -0.10
    AtA
    -0.09
     addCriterion
    -0.09
    redd
    -0.09
    以ä¸ĭ
    -0.08
     odv
    -0.08
    adge
    -0.08
    'gc
    -0.08
    §Ãĥ
    -0.08
    POSITIVE LOGITS
     Rosenstein
    0.08
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.08
    https
    0.08
     EP
    0.08
    False
    0.07
     Georges
    0.07
    citation
    0.07
     Condition
    0.07
     numel
    0.07
    ï¿
    0.07
    Activations Density 0.206%

    No Known Activations