© 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. 15787
    Prev
    Next
    INDEX
    Explanations

    uses Usenet OR SharePoint

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

    function words that link clauses or phrases—especially conjunctions, prepositions, and clause-separating punctuation.

    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
    ¶Į
    -0.11
    offline
    -0.10
    itest
    -0.10
    ÂĢÂĢ
    -0.10
    ******č\n
    -0.10
     handset
    -0.10
    łéĻ¤
    -0.09
    ¦æĥħ
    -0.09
    ertools
    -0.09
    lectron
    -0.09
    POSITIVE LOGITS
     internet
    0.17
     Internet
    0.16
     Thunder
    0.13
     phone
    0.12
     Outlook
    0.12
     web
    0.12
     mobile
    0.11
     outlook
    0.11
     physical
    0.11
     Intern
    0.10
    Activations Density 0.727%

    No Known Activations