© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 7896
    Prev
    Next
    INDEX
    Explanations

    concern, worry, care

    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
    Negative Logits
    ï½ī
    -0.09
    æ²Ļ
    -0.09
    å¯
    -0.08
    è¯
    -0.08
     Treat
    -0.08
    oust
    -0.08
     indul
    -0.08
     Exped
    -0.08
    ;;
    -0.08
     /\n\n
    -0.08
    POSITIVE LOGITS
     concern
    0.60
     concerned
    0.51
     preocup
    0.46
     concerns
    0.45
     worry
    0.43
    Concern
    0.42
     Concern
    0.41
     worried
    0.39
     worries
    0.34
     care
    0.31
    Activations Density 0.140%

    No Known Activations