© 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. 64339
    Prev
    Next
    INDEX
    Explanations

    advising what should happen

    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
     пÑĢидеÑĤÑģÑı
    -0.11
    onda
    -0.09
     gonna
    -0.09
     DOES
    -0.08
    ê²łëĭ¤
    -0.08
    ãĤĵãģª
    -0.08
     WILL
    -0.08
    reau
    -0.08
    will
    -0.08
    (can
    -0.08
    POSITIVE LOGITS
     should
    0.62
     Should
    0.50
    åºĶ该
    0.49
    should
    0.49
    Should
    0.46
     nên
    0.43
     sollten
    0.40
     sollte
    0.40
     shouldn
    0.39
     deber
    0.38
    Activations Density 0.242%

    No Known Activations