© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 56511
    Prev
    Next
    INDEX
    Explanations

    suggestion that, project are

    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
    ertino
    -0.10
    ¨¨
    -0.08
     knull
    -0.08
     огÑĢа
    -0.08
    ingleton
    -0.08
    bsolute
    -0.08
    clusive
    -0.08
    MBProgressHUD
    -0.07
    malink
    -0.07
     имÑĥ
    -0.07
    POSITIVE LOGITS
    uu
    0.09
    âĶĤ
    0.09
     PL
    0.09
     [
    0.09
     myfile
    0.08
    etti
    0.08
     in
    0.08
    0.08
     overt
    0.08
     prer
    0.08
    Activations Density 0.211%

    No Known Activations