© 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. 36588
    Prev
    Next
    INDEX
    Explanations

    he, him, his

    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
     iddi
    -0.13
    她们
    -0.13
     haar
    -0.13
     herself
    -0.11
    Ðĩ
    -0.11
    تÙĩا
    -0.10
    彼女
    -0.10
     jejÃŃ
    -0.10
    ovalo
    -0.10
    ledi
    -0.10
    POSITIVE LOGITS
     him
    0.57
    ä»ĸ
    0.46
     he
    0.41
     lui
    0.38
     ä»ĸ
    0.37
     ihn
    0.35
     ông
    0.35
     вÑĸн
    0.35
     his
    0.34
     него
    0.34
    Activations Density 0.179%

    No Known Activations