© 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. 25199
    Prev
    Next
    INDEX
    Explanations

    development and production

    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
    ÂĢÂĢ
    -0.10
     Garn
    -0.09
    ullan
    -0.09
     ephem
    -0.09
    bil
    -0.08
    StartPosition
    -0.08
     Conv
    -0.08
     Advis
    -0.08
     namoro
    -0.08
    ContentSize
    -0.08
    POSITIVE LOGITS
     manufacture
    0.20
     manufacturing
    0.20
     production
    0.19
     manufacturer
    0.15
    production
    0.14
    åĪ¶éĢł
    0.14
     Manufacturing
    0.14
     sale
    0.13
     manufactured
    0.13
    /or
    0.13
    Activations Density 0.020%

    No Known Activations