© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 21470
    Prev
    Next
    INDEX
    Explanations

    past participles or verb endings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     beaten
    -0.10
    âĶ¬
    -0.10
    даÑİÑĤ
    -0.10
     hacen
    -0.10
    aban
    -0.10
    owaÄĩ
    -0.10
     blown
    -0.10
    ÑĤÑĮÑģÑı
    -0.10
    å®ļçļĦ
    -0.10
    νονÏĦαι
    -0.10
    POSITIVE LOGITS
    ÏīÏĥε
    0.21
    uvo
    0.21
    ió
    0.21
     yaptı
    0.20
     baktı
    0.20
    ãģĹãģ¾ãģĹãģŁ
    0.20
    äºĨä¸Ģ
    0.19
     hizo
    0.18
    åĩºäºĨ
    0.18
    ÏĦηÏĥε
    0.17
    Activations Density 0.075%

    No Known Activations