© 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. 34201
    Prev
    Next
    INDEX
    Explanations

    proper noun prefix

    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
    iders
    -0.10
     Bris
    -0.10
     Lau
    -0.10
     Gui
    -0.09
     Dude
    -0.08
    ãģ¡ãģ¯
    -0.08
    ijing
    -0.08
    gree
    -0.08
    wechat
    -0.08
     rake
    -0.08
    POSITIVE LOGITS
    ische
    0.16
    isch
    0.14
    ischer
    0.12
    ischen
    0.12
     language
    0.12
    ìĿĺ
    0.11
     government
    0.11
    isches
    0.11
    lish
    0.11
    style
    0.10
    Activations Density 0.043%

    No Known Activations