© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 59588
    Prev
    Next
    INDEX
    Explanations

    in Japan

    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
     Hok
    -0.12
     Osaka
    -0.11
     Miy
    -0.11
     Citation
    -0.10
     Shib
    -0.10
     sushi
    -0.10
    kart
    -0.10
    몰
    -0.09
     ëĦ¤ìĿ´íĬ¸
    -0.09
    aksi
    -0.09
    POSITIVE LOGITS
     ç®
    0.14
     Ow
    0.13
     Mt
    0.12
    ç®±
    0.11
     Od
    0.11
     Lake
    0.11
     Ash
    0.11
    çĶ²
    0.10
    iry
    0.10
     Ont
    0.10
    Activations Density 0.019%

    No Known Activations