© 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. 9848
    Prev
    Next
    INDEX
    Explanations

    name after 's or your

    np_acts-logits-general · gemini-2.5-flash-lite

    possessive forms (apostrophe-s) indicating ownership or association.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    Naming
    -0.09
    ë¶
    -0.09
    stal
    -0.09
    egend
    -0.09
     Nep
    -0.09
     Gn
    -0.09
     ÐĿаз
    -0.09
     Duy
    -0.09
    Surname
    -0.09
     Masc
    -0.08
    POSITIVE LOGITS
     name
    0.48
    name
    0.35
     Name
    0.32
    .name
    0.29
     names
    0.28
    Name
    0.28
    \tname
    0.27
    åIJįåŃĹ
    0.27
    _name
    0.26
     NAME
    0.25
    Activations Density 0.149%

    No Known Activations