© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    meeting begin

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ि,
    -0.09
     zwar
    -0.09
    ãĤĤãģĹ
    -0.08
    ãĢijãĢIJ
    -0.08
    Unless
    -0.08
    While
    -0.08
    izzle
    -0.08
    ynam
    -0.08
     наÑģÑĤ
    -0.07
     EITHER
    -0.07
    POSITIVE LOGITS
    ÂĢÂĢ
    0.12
    ¦æĥħ
    0.10
     ÑĤоже
    0.09
    ¶Į
    0.09
     GOODMAN
    0.08
    uien
    0.08
    actionDate
    0.08
    εδ
    0.08
    orget
    0.08
    )prepare
    0.08
    Activations Density 0.141%

    No Known Activations