© 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. 46027
    Prev
    Next
    INDEX
    Explanations

    sadness and disappointment

    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
     Downs
    -0.10
     embarrassing
    -0.10
     disgusted
    -0.10
    üf
    -0.10
    Ì
    -0.09
     nightmares
    -0.09
     Ske
    -0.09
     disgusting
    -0.09
     uncomfortable
    -0.09
     nightmare
    -0.09
    POSITIVE LOGITS
     disappointment
    0.36
     disappointed
    0.34
     sad
    0.32
     disappointing
    0.29
     Sad
    0.29
    Sad
    0.29
     disappoint
    0.27
     sadness
    0.25
    sad
    0.24
    bum
    0.23
    Activations Density 0.091%

    No Known Activations