© 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. 17394
    Prev
    Next
    INDEX
    Explanations

    fatherhood, DNA, and adoption

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

    The neuron responds to sentence-structure scaffolding—function words, auxiliaries, and list/section markers that signal instructions or simple narrative clauses.

    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
     matrimon
    -0.11
     marital
    -0.11
     home
    -0.10
     prenatal
    -0.10
     parch
    -0.09
    éĭ
    -0.09
     Anniversary
    -0.09
     unborn
    -0.09
    à¸Ĭม
    -0.09
    cky
    -0.09
    POSITIVE LOGITS
     father
    0.22
     illeg
    0.18
    father
    0.18
     DNA
    0.17
     adoption
    0.17
    DNA
    0.16
     pat
    0.16
     fathers
    0.16
     conception
    0.15
     dna
    0.14
    Activations Density 0.083%

    No Known Activations