© 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. 40373
    Prev
    Next
    INDEX
    Explanations

    le livre, experienced secretary

    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
     geschichten
    -0.08
    pgsql
    -0.08
    [,]
    -0.07
     canh
    -0.07
     Lump
    -0.07
    Ê
    -0.07
    ulen
    -0.07
     Ea
    -0.07
    Ñģли
    -0.07
    /span
    -0.07
    POSITIVE LOGITS
    EMPLARY
    0.12
    åĪļæīį
    0.10
     Mühendis
    0.09
    .***.***
    0.09
     aforementioned
    0.09
    éĤ£ä¸ª
    0.09
    ¶Į
    0.08
     EXEMPLARY
    0.08
     baģlantılar
    0.08
    \Php
    0.08
    Activations Density 0.390%

    No Known Activations