© 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. 4631
    Prev
    Next
    INDEX
    Explanations

    possessive 'their' and associated nouns

    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
     yourself
    -0.11
    /Dk
    -0.11
     yourselves
    -0.11
    ä½łä»¬
    -0.10
    âĢŀTo
    -0.09
     chúng
    -0.09
    ãĤ¤ãĥ¤
    -0.09
     nick
    -0.09
    å®ĥ们
    -0.08
    defgroup
    -0.08
    POSITIVE LOGITS
     themselves
    0.39
     their
    0.25
     Their
    0.24
    Their
    0.22
    their
    0.22
     thems
    0.18
    ï¼Įä»ĸ们
    0.18
     loro
    0.18
     иÑħ
    0.17
     leurs
    0.17
    Activations Density 0.146%

    No Known Activations