© 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. 26976
    Prev
    Next
    INDEX
    Explanations

    critique and clarify

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

    meta-instructional language requesting critique, edits, analysis, clarification, or organizational structuring of content (e.g., agendas/titles)

    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
    ÂĢÂĢ
    -0.11
    ¶Į
    -0.11
    ******č\n
    -0.11
    -------------</
    -0.10
    .opensource
    -0.10
    .Formatter
    -0.10
     salopes
    -0.09
    ¦æĥħ
    -0.09
    using
    -0.09
    ----------</
    -0.09
    POSITIVE LOGITS
     dp
    0.09
    âĢ¦âĢ¦
    0.07
    marvin
    0.07
     [...
    0.07
     "...
    0.06
    .Pod
    0.06
    0.06
    ÂŃi
    0.06
    oldt
    0.06
    dp
    0.06
    Activations Density 5.647%

    No Known Activations