© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30021
    Prev
    Next
    INDEX
    Explanations

    is/are typically

    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
    illet
    -0.09
     BaseService
    -0.09
    eteria
    -0.09
    uien
    -0.08
    728
    -0.08
     Tribe
    -0.08
    pga
    -0.08
    -established
    -0.08
    578
    -0.08
     çľ
    -0.08
    POSITIVE LOGITS
     usually
    0.26
     best
    0.23
     typically
    0.21
    usually
    0.19
     обÑĭÑĩно
    0.18
    éĢļ常
    0.18
     often
    0.18
     Usually
    0.17
     custom
    0.16
     thÆ°á»Ŀng
    0.15
    Activations Density 0.119%

    No Known Activations