© 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. 20801
    Prev
    Next
    INDEX
    Explanations

    good or bad

    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
     неÑĢ
    -0.10
    ÙĪÙĬر
    -0.09
    acie
    -0.09
    zes
    -0.09
    ilden
    -0.08
     seins
    -0.08
    ÑĤеÑĢн
    -0.08
    ayd
    -0.08
    heiro
    -0.08
    ATER
    -0.08
    POSITIVE LOGITS
     bad
    0.32
    bad
    0.25
     evil
    0.24
    åĿı
    0.23
     Bad
    0.23
    Bad
    0.22
    æĤª
    0.20
    evil
    0.20
     Evil
    0.20
    _bad
    0.19
    Activations Density 0.063%

    No Known Activations