© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37643
    Prev
    Next
    INDEX
    Explanations

    split into parts

    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
     subdivision
    -0.11
     subdiv
    -0.10
     subdivisions
    -0.10
    768
    -0.09
    sez
    -0.09
    ibu
    -0.09
    383
    -0.09
    933
    -0.09
    ï½°
    -0.09
    ä¹ĭä¸Ģ
    -0.09
    POSITIVE LOGITS
     smaller
    0.26
     separate
    0.16
     mnie
    0.14
     its
    0.13
     smallest
    0.13
     component
    0.12
     individual
    0.12
     different
    0.12
     distinct
    0.12
     оÑĤделÑĮ
    0.12
    Activations Density 0.064%

    No Known Activations