© 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. 217
    Prev
    Next
    INDEX
    Explanations

    follow these steps

    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
    ÏįÏĦε
    -0.11
     fos
    -0.09
    ena
    -0.09
     Desired
    -0.09
    uis
    -0.08
    aniem
    -0.08
    chan
    -0.08
    ä¸įäºĨ
    -0.08
     ÑĤÑĢебÑĥеÑĤ
    -0.08
    iment
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥
    0.13
     puedes
    0.13
     you
    0.13
    ï¼Įåı¯ä»¥
    0.12
    ä½ł
    0.12
     ä½ł
    0.12
     можеÑĤе
    0.12
     Hayes
    0.12
     need
    0.12
    ามารà¸ĸ
    0.12
    Activations Density 0.115%

    No Known Activations