© 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. 48900
    Prev
    Next
    INDEX
    Explanations

    going goingat workmore beautifulyour mind

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

    function words that serve grammatical glue—prepositions, auxiliaries, determiners/pronouns, comparative markers, and other short connectors.

    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
     ragaz
    -0.09
    ¶Į
    -0.09
    ascript
    -0.08
     Erotische
    -0.08
    ******č\n
    -0.08
    unma
    -0.08
    âĸ¡
    -0.08
    ombine
    -0.08
    ekim
    -0.08
     Ulus
    -0.08
    POSITIVE LOGITS
    &apos
    0.10
    č
    0.09
     č
    0.08
     "'
    0.08
    ÂŃi
    0.08
     ¶
    0.08
     ³³ ³³
    0.07
    ÂŃing
    0.07
     ...)\n
    0.07
     ...)
    0.06
    Activations Density 8.444%

    No Known Activations