© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18758
    Prev
    Next
    INDEX
    Explanations

    forms of having

    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
    Negative Logits
    âĢIJâĢIJ
    -0.09
    ecture
    -0.09
     Rena
    -0.08
    ahun
    -0.08
    obl
    -0.08
    bor
    -0.08
     Jenkins
    -0.08
    abit
    -0.08
    aira
    -0.08
    .angular
    -0.07
    POSITIVE LOGITS
     having
    0.70
     Having
    0.60
    having
    0.57
    Having
    0.56
     имеÑĤÑĮ
    0.39
     memiliki
    0.38
     avoir
    0.35
    æĭ¥æľī
    0.35
     avere
    0.35
     tener
    0.34
    Activations Density 0.234%

    No Known Activations