© 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. 42642
    Prev
    Next
    INDEX
    Explanations

    process requires

    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
    oki
    -0.09
     çij
    -0.09
    TestMethod
    -0.09
    ãģ¨ãģ¯
    -0.09
    achs
    -0.09
     Moran
    -0.08
     Comes
    -0.08
    eren
    -0.08
    FromBody
    -0.08
    ç¯Ħ
    -0.08
    POSITIVE LOGITS
     require
    0.15
     requires
    0.14
     requ
    0.12
     yêu
    0.11
     cul
    0.10
     Require
    0.10
     Requires
    0.10
    requires
    0.10
     exact
    0.10
    requ
    0.10
    Activations Density 0.021%

    No Known Activations