© 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. 36591
    Prev
    Next
    INDEX
    Explanations

    harmful, unethical, racist, sexist

    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
     trimest
    -0.09
     Medicaid
    -0.09
     ë¨
    -0.09
     arrog
    -0.09
    quier
    -0.08
     Ply
    -0.08
    .linkedin
    -0.08
    ãİ
    -0.08
     Kickstarter
    -0.08
    á»įc
    -0.08
    POSITIVE LOGITS
     violent
    0.11
     rac
    0.11
     violence
    0.11
     graphic
    0.10
     offensive
    0.10
     illegal
    0.10
     nor
    0.09
     copyrighted
    0.09
     mature
    0.09
     Seas
    0.09
    Activations Density 0.028%

    No Known Activations