© 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. 18462
    Prev
    Next
    INDEX
    Explanations

    fictional spell chanting

    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
     Rivers
    -0.10
     greeting
    -0.10
    uluk
    -0.10
     mir
    -0.10
     arrow
    -0.10
     mute
    -0.09
     prom
    -0.09
     silence
    -0.09
     Opr
    -0.09
    assi
    -0.09
    POSITIVE LOGITS
     rec
    0.25
     chant
    0.21
    chant
    0.20
    念
    0.20
     inc
    0.20
     chanting
    0.18
     chants
    0.17
     mantra
    0.17
    CHANT
    0.16
     niá»ĩm
    0.16
    Activations Density 0.054%

    No Known Activations