© 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. 18225
    Prev
    Next
    INDEX
    Explanations

    unethical, killer, necessary, high

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

    function words that serve as grammatical connectors (especially conjunctions, prepositions, and simple determiners/pronouns).

    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
     aforementioned
    -0.09
    INCLUDED
    -0.08
    íĨłíĨł
    -0.08
     councill
    -0.07
    ãĤ£
    -0.07
     afore
    -0.07
     CONSEQUENTIAL
    -0.07
    ฺ
    -0.07
    .generated
    -0.07
    ĴĮ
    -0.07
    POSITIVE LOGITS
    ãĥ¼ãĥ¼
    0.09
    idUser
    0.08
     hereby
    0.08
     myself
    0.08
    Coder
    0.08
    _Lean
    0.08
     %[
    0.07
    ​\n\n
    0.07
    _mD
    0.07
     [âĢ¦
    0.07
    Activations Density 0.012%

    No Known Activations