© 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. 1753
    Prev
    Next
    INDEX
    Explanations

    a/an iterative method or algorithm

    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
    outing
    -0.10
    aje
    -0.09
    ElementsBy
    -0.09
     modifiers
    -0.08
     Followers
    -0.08
    943
    -0.08
     Walt
    -0.08
    554
    -0.08
     Gum
    -0.08
    elsing
    -0.08
    POSITIVE LOGITS
     technique
    0.20
    ä¸Ģç§į
    0.16
     popular
    0.16
     Technique
    0.16
     widely
    0.14
     type
    0.14
     method
    0.14
     powerful
    0.12
    popular
    0.12
     supervised
    0.12
    Activations Density 0.169%

    No Known Activations