© 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. 47309
    Prev
    Next
    INDEX
    Explanations

    daring and challenges

    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
    r
    -0.11
    ĥģ
    -0.10
    yx
    -0.09
    iske
    -0.09
    rij
    -0.09
    eten
    -0.09
    opia
    -0.09
    l
    -0.09
    lain
    -0.09
    omial
    -0.09
    POSITIVE LOGITS
    devil
    0.23
    -do
    0.11
     enough
    0.10
    ffen
    0.10
    wolf
    0.10
     fate
    0.10
    bell
    0.10
    æķ¢
    0.10
     devil
    0.09
     Devil
    0.09
    Activations Density 0.015%

    No Known Activations