© 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. 41890
    Prev
    Next
    INDEX
    Explanations

    requests and commands

    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
    appers
    -0.09
    MMC
    -0.09
     æ¼
    -0.08
     Gallagher
    -0.08
    ismu
    -0.08
    ｨ
    -0.08
    ç©´
    -0.08
    ikon
    -0.07
     Îļά
    -0.07
    apper
    -0.07
    POSITIVE LOGITS
    .scalablytyped
    0.09
    iyim
    0.09
    anol
    0.09
     ev
    0.08
    ÑĩаÑĤ
    0.08
    .LENGTH
    0.08
    _TestCase
    0.08
    ìĩ
    0.08
    stÅĻÃŃ
    0.08
    ,､
    0.08
    Activations Density 0.041%

    No Known Activations