© 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. 11571
    Prev
    Next
    INDEX
    Explanations

    That's why, what, how, something

    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
    aler
    -0.11
    raq
    -0.10
     quale
    -0.09
    ãĥ¾
    -0.09
    éĤ£ä¹Ī
    -0.09
    çķ
    -0.09
    awn
    -0.09
     rather
    -0.09
    ãģĦ
    -0.09
    sak
    -0.09
    POSITIVE LOGITS
     why
    0.20
     what
    0.15
    why
    0.14
     where
    0.13
    为ä»Ģä¹Ī
    0.12
     pourquoi
    0.11
     something
    0.10
    what
    0.10
    where
    0.10
     поÑĩемÑĥ
    0.10
    Activations Density 0.029%

    No Known Activations