© 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. 15485
    Prev
    Next
    INDEX
    Explanations

    saying something hurtful

    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
    说è¯Ŀ
    -0.11
    onde
    -0.10
    ansi
    -0.10
    oup
    -0.10
    ERGE
    -0.10
    âĶ´
    -0.10
    íĵ¨
    -0.09
    讲
    -0.09
    /licenses
    -0.09
    REAM
    -0.09
    POSITIVE LOGITS
     kepada
    0.11
     Trem
    0.10
     Lon
    0.10
     secrets
    0.10
    çľ
    0.09
     truth
    0.09
     insensitive
    0.09
     hurt
    0.09
     Secrets
    0.09
     disob
    0.09
    Activations Density 0.088%

    No Known Activations