© 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. 61614
    Prev
    Next
    INDEX
    Explanations

    Gather needed items or resources

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

    It detects step-by-step instructional content, especially numbered list steps and imperative “materials/resources/ingredients needed” lines.

    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
    (URL
    -0.08
    _,,
    -0.08
     tzv
    -0.07
     tod
    -0.07
    .tbl
    -0.07
    .shiro
    -0.07
    ::|
    -0.07
     ninete
    -0.07
     EN
    -0.06
    .lucene
    -0.06
    POSITIVE LOGITS
    ¶Į
    0.09
    EMPLARY
    0.08
    _inches
    0.07
    ê¸Ķ
    0.07
    ucher
    0.07
    _Invoke
    0.07
     orderby
    0.07
    infra
    0.07
    onus
    0.06
    .RightToLeft
    0.06
    Activations Density 4.285%

    No Known Activations