© 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. 43874
    Prev
    Next
    INDEX
    Explanations

    have / tener

    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
     Hasan
    -0.11
    htags
    -0.09
    éģŃ
    -0.09
     aff
    -0.08
    arma
    -0.08
    482
    -0.08
     giÃłnh
    -0.08
     Hague
    -0.08
    æ£ļ
    -0.08
    _MUTEX
    -0.08
    POSITIVE LOGITS
     memiliki
    0.24
    æľīä¸Ģ
    0.23
     have
    0.22
    æľī
    0.20
     avere
    0.18
     имеÑİÑĤ
    0.18
     having
    0.17
     имееÑĤ
    0.17
     داراÛĮ
    0.17
     tiene
    0.16
    Activations Density 0.206%

    No Known Activations