© 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. 28766
    Prev
    Next
    INDEX
    Explanations

    consider, visit, explore, solve

    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
    s
    -0.10
     Anton
    -0.10
     tread
    -0.09
    es
    -0.09
    ses
    -0.09
     unre
    -0.09
    (s
    -0.09
     Wel
    -0.08
     Marc
    -0.08
    ly
    -0.08
    POSITIVE LOGITS
    åĪ°çļĦ
    0.12
    azu
    0.11
    /include
    0.11
    ableView
    0.10
    abet
    0.10
    ãĢĢãĥİ
    0.10
     Michaels
    0.09
    946
    0.09
     Ukra
    0.09
    ãĢĢãĤĿ
    0.09
    Activations Density 0.108%

    No Known Activations