© 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. 39622
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    pronouns, especially third-person and anaphoric references like “it” and “that,” indicating coreference to people or things.

    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
    PN
    -0.08
     NotImplemented
    -0.08
    .MixedReality
    -0.08
    èĥ¶
    -0.07
     Stateless
    -0.07
     Äijá»Ļc
    -0.07
    /animations
    -0.07
    âĢŀP
    -0.07
     à¸ģรà¸ģ
    -0.07
     inval
    -0.07
    POSITIVE LOGITS
    htable
    0.08
    OLON
    0.08
    733
    0.08
    ims
    0.07
    icket
    0.07
    IMS
    0.07
     Fir
    0.07
     Spicer
    0.07
     limburg
    0.07
    shelf
    0.07
    Activations Density 0.687%

    No Known Activations