© 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. 7951
    Prev
    Next
    INDEX
    Explanations

    defining concepts

    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
    esta
    -0.09
     ap
    -0.09
     Trojan
    -0.09
     å¸
    -0.08
     Bale
    -0.08
     EITHER
    -0.08
     wo
    -0.08
     particularly
    -0.08
    464
    -0.08
    ä½µ
    -0.08
    POSITIVE LOGITS
     definition
    0.12
    å®ļä¹ī
    0.11
     Definition
    0.10
     def
    0.10
    definition
    0.10
     pornos
    0.10
     تعرÛĮÙģ
    0.10
     Appet
    0.10
     Webster
    0.09
    Definition
    0.09
    Activations Density 0.197%

    No Known Activations