© 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. 33835
    Prev
    Next
    INDEX
    Explanations

    Note, Chapters, contractions

    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
     blink
    -0.09
     Ach
    -0.08
     ass
    -0.08
     eng
    -0.08
     Interview
    -0.08
     Billy
    -0.08
     Replies
    -0.08
     backing
    -0.08
     Dam
    -0.08
     open
    -0.08
    POSITIVE LOGITS
     note
    0.10
    tsy
    0.10
     Note
    0.10
    eldorf
    0.09
    (Note
    0.09
    ISED
    0.09
    Note
    0.09
     NOTE
    0.09
    uby
    0.09
    fty
    0.09
    Activations Density 0.026%

    No Known Activations