© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37825
    Prev
    Next
    INDEX
    Explanations

    learn about, dive deep, create plan, comprehensive overview

    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
     zbyt
    -0.10
     OVERRIDE
    -0.09
    illi
    -0.08
    اÙĥÙĨ
    -0.08
    adesh
    -0.08
     непоÑģÑĢед
    -0.08
     pure
    -0.07
    isContained
    -0.07
     znaj
    -0.07
    .lv
    -0.07
    POSITIVE LOGITS
     comprehensive
    0.19
    åħ¨éĿ¢
    0.16
    综åIJĪ
    0.16
     compreh
    0.16
     Comprehensive
    0.15
     overall
    0.14
    å®Įæķ´
    0.14
     hol
    0.14
    prehensive
    0.13
     complete
    0.13
    Activations Density 0.932%

    No Known Activations