© 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. 40209
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

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

    third-person singular gendered subject pronouns referring to the patient, especially at the start of clinical sentences.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     ext
    -0.10
     sor
    -0.09
    ï½Ģãĥ½
    -0.09
    tracted
    -0.09
    ling
    -0.09
    uche
    -0.09
     Hund
    -0.08
     Sor
    -0.08
    ulla
    -0.08
    737
    -0.08
    POSITIVE LOGITS
     notice
    0.16
     noticed
    0.13
    notice
    0.12
    æľį
    0.12
     smoke
    0.12
     notices
    0.12
     noticing
    0.12
     feel
    0.12
     Notice
    0.11
     attribute
    0.11
    Activations Density 0.042%

    No Known Activations