© 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. 29025
    Prev
    Next
    INDEX
    Explanations

    data has no first

    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
     Surround
    -0.09
     incarn
    -0.09
    Normalization
    -0.09
     Shank
    -0.09
     Dah
    -0.09
     nuest
    -0.09
    มà¸Ļ
    -0.09
    _mC
    -0.09
    uxtap
    -0.09
    _Db
    -0.09
    POSITIVE LOGITS
     fract
    0.15
     emerg
    0.13
     Self
    0.13
     substrate
    0.13
     self
    0.12
     Layer
    0.12
     meta
    0.11
     attract
    0.11
     Observer
    0.11
    quine
    0.11
    Activations Density 0.204%

    No Known Activations