© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23626
    Prev
    Next
    INDEX
    Explanations

    introductions and clauses

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

    message-structure and formatting markers, especially turn boundaries, line breaks, and question/closing 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
    akh
    -0.10
    illi
    -0.10
    OrNull
    -0.09
    this
    -0.08
     Beaut
    -0.08
     this
    -0.08
     ÑįÑĤо
    -0.08
     sto
    -0.08
    This
    -0.08
    bek
    -0.08
    POSITIVE LOGITS
     when
    0.43
    when
    0.34
     When
    0.30
     khi
    0.30
    When
    0.29
     quando
    0.29
     ÙĩÙĨگاÙħ
    0.29
     när
    0.26
     lors
    0.25
     когда
    0.25
    Activations Density 0.371%

    No Known Activations