© 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. 21338
    Prev
    Next
    INDEX
    Explanations

    fake or impersonation

    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
     disguised
    -0.11
     blinded
    -0.10
     Ih
    -0.09
     Lap
    -0.09
     nos
    -0.09
     coded
    -0.09
     wrongdoing
    -0.09
     Bilder
    -0.09
     Forget
    -0.09
     ob
    -0.09
    POSITIVE LOGITS
     forg
    0.24
     fake
    0.23
     giả
    0.22
    åĨĴ
    0.22
     imperson
    0.22
    fake
    0.21
     impost
    0.21
    Fake
    0.20
     Forg
    0.20
    åģĩ
    0.20
    Activations Density 0.157%

    No Known Activations