© 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. 10738
    Prev
    Next
    INDEX
    Explanations

    AI self-description limitations

    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
     Cas
    -0.10
     Piet
    -0.09
     Fah
    -0.09
    ogan
    -0.09
     Maxim
    -0.09
    herits
    -0.09
     Äijỡ
    -0.09
     Rita
    -0.08
     AUTO
    -0.08
     Betty
    -0.08
    POSITIVE LOGITS
    èīĩ
    0.10
     exist
    0.10
    esch
    0.09
     impro
    0.09
    ubat
    0.09
     committed
    0.09
     disap
    0.09
     neutr
    0.08
     Roose
    0.08
    ÃĿ
    0.08
    Activations Density 0.077%

    No Known Activations