© 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. 38413
    Prev
    Next
    INDEX
    Explanations

    vocal delivery characteristics

    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
     spelling
    -0.11
     Lingu
    -0.11
    uling
    -0.11
    Verb
    -0.10
    YM
    -0.10
     spells
    -0.10
     linguistic
    -0.10
     lingu
    -0.09
    mtx
    -0.09
    verb
    -0.09
    POSITIVE LOGITS
     int
    0.31
     pros
    0.26
     delivery
    0.26
     accent
    0.24
    inton
    0.23
     pitch
    0.23
     inf
    0.23
     cad
    0.22
     Pros
    0.21
     Delivery
    0.21
    Activations Density 0.115%

    No Known Activations