© 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. 38279
    Prev
    Next
    INDEX
    Explanations

    technical terms and arguments

    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
    ä½ľä¸º
    -0.15
     sebagai
    -0.15
     jako
    -0.14
     als
    -0.14
     kao
    -0.12
     as
    -0.10
     каÑĩеÑģÑĤве
    -0.10
    yaw
    -0.10
     ÏīÏĤ
    -0.09
    pv
    -0.09
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.12
    991
    0.10
     Enlight
    0.09
    288
    0.09
    éŀ
    0.09
     Katrina
    0.08
     viable
    0.08
    acers
    0.08
    DEX
    0.08
     Tactics
    0.08
    Activations Density 0.227%

    No Known Activations