© 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. 10766
    Prev
    Next
    INDEX
    Explanations

    may choose to express opinions or offensive language

    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
     athe
    -0.10
     Müslüman
    -0.10
     Muslims
    -0.09
    icha
    -0.09
     bet
    -0.09
     Muslim
    -0.09
     Zen
    -0.09
    clist
    -0.09
     atheist
    -0.09
     prejud
    -0.09
    POSITIVE LOGITS
     pros
    0.20
    indo
    0.16
     intoler
    0.15
     Crus
    0.14
     intolerance
    0.14
    Pros
    0.14
     exclus
    0.13
     exclusive
    0.12
     Fan
    0.12
     Pros
    0.12
    Activations Density 0.087%

    No Known Activations