© 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. 28254
    Prev
    Next
    INDEX
    Explanations

    one-to-one, don't, time, 30 words, 5-word

    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
     Ä°mpar
    -0.07
     Marian
    -0.07
    v
    -0.07
    "
    -0.07
    ,č\nč\n
    -0.07
     applicationContext
    -0.07
    RunWith
    -0.06
     ÃĤ
    -0.06
     dames
    -0.06
     Walters
    -0.06
    POSITIVE LOGITS
     -*-č\n
    0.10
     Ulus
    0.09
    ÂĢÂĢ
    0.09
    LEGRO
    0.09
    Ìģ
    0.09
     ragaz
    0.09
    ¦æĥħ
    0.09
    interopRequire
    0.08
    -ÐŁÐµÑĤеÑĢб
    0.08
    пÑĢимеÑĢ
    0.08
    Activations Density 0.025%

    No Known Activations