© 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. 1659
    Prev
    Next
    INDEX
    Explanations

    created by calling the

    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
     automatically
    -0.12
     preset
    -0.11
    rint
    -0.09
     imperson
    -0.09
     involuntary
    -0.09
     aud
    -0.09
     automat
    -0.09
    eum
    -0.08
    cie
    -0.08
     programm
    -0.08
    POSITIVE LOGITS
     manual
    0.45
    manual
    0.39
     Manual
    0.38
    Manual
    0.37
     manually
    0.35
     MANUAL
    0.32
    .manual
    0.32
    _manual
    0.31
    /manual
    0.27
    æīĭ
    0.25
    Activations Density 0.197%

    No Known Activations