© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 939
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by action verbs

    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
     fruits
    -0.10
    acher
    -0.09
    .cgi
    -0.09
    kal
    -0.09
     Cove
    -0.09
     æĴ
    -0.09
     Bers
    -0.09
     Cob
    -0.08
    plat
    -0.08
     Bryce
    -0.08
    POSITIVE LOGITS
     doing
    0.47
    åģļ
    0.38
     Doing
    0.36
    doing
    0.34
    Doing
    0.33
     melakukan
    0.33
     accompl
    0.26
     اÙĨجاÙħ
    0.26
     accomplish
    0.23
     perform
    0.22
    Activations Density 0.229%

    No Known Activations