© 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. 11376
    Prev
    Next
    INDEX
    Explanations

    singing

    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
     jazz
    -0.12
    CRT
    -0.10
     Jazz
    -0.10
     violin
    -0.09
     Mozart
    -0.09
    432
    -0.09
     spoken
    -0.09
    yor
    -0.09
    aln
    -0.09
     elo
    -0.09
    POSITIVE LOGITS
     sing
    0.43
     Sing
    0.39
     kar
    0.37
     singing
    0.34
    Sing
    0.33
    sing
    0.30
     Kar
    0.28
     sang
    0.27
    åĶ±
    0.27
     sings
    0.27
    Activations Density 0.062%

    No Known Activations