© 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. 58710
    Prev
    Next
    INDEX
    Explanations

    numbered lists and parenthetical clauses

    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
    rient
    -0.09
     Gon
    -0.08
     Poe
    -0.08
     Batt
    -0.08
    quin
    -0.08
    .responses
    -0.08
     conv
    -0.08
     Gin
    -0.08
     dof
    -0.08
    ught
    -0.08
    POSITIVE LOGITS
    etc
    0.11
     finally
    0.09
     Cheney
    0.09
    /Framework
    0.08
    orderid
    0.08
     Pazar
    0.08
    ango
    0.08
     etc
    0.08
    ÙĪص
    0.08
    azes
    0.08
    Activations Density 0.003%

    No Known Activations