© 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. 1879
    Prev
    Next
    INDEX
    Explanations

    synthetic insectoids

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

    structural or formatting markers—boundary/separator tokens and short connective elements that signal document structure rather than content

    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
    ÑģÑĤе
    -0.10
    aylor
    -0.09
     withString
    -0.09
    alace
    -0.09
    tring
    -0.08
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.08
    agal
    -0.08
     ÑĤабли
    -0.08
    icontrol
    -0.08
    elps
    -0.08
    POSITIVE LOGITS
    0.08
    673
    0.08
    .impl
    0.08
     CX
    0.08
     cred
    0.08
    erialized
    0.08
     Dame
    0.07
    stitute
    0.07
    orous
    0.07
     Kern
    0.07
    Activations Density 0.294%

    No Known Activations