© 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. 10529
    Prev
    Next
    INDEX
    Explanations

    important or key aspects

    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
    missive
    -0.10
    ìĿ´ëĿ¼ëĬĶ
    -0.09
    ëĿ¼ëĬĶ
    -0.09
    èĪ¬
    -0.08
     something
    -0.08
    IIIK
    -0.08
     mÃŃnimo
    -0.08
    reff
    -0.08
    heavy
    -0.08
    æŁIJ
    -0.08
    POSITIVE LOGITS
     important
    0.11
    éĩįè¦ģ
    0.10
     importante
    0.10
     whose
    0.10
    clave
    0.10
     crucial
    0.10
     ÙħÙĩÙħ
    0.08
     amb
    0.08
    é«
    0.08
    lap
    0.08
    Activations Density 0.085%

    No Known Activations