© 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. 63971
    Prev
    Next
    INDEX
    Explanations

    becomes

    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
    estroy
    -0.09
     Fres
    -0.09
    igy
    -0.09
    BST
    -0.09
     ultimately
    -0.09
    imbus
    -0.08
    umin
    -0.08
    ZE
    -0.08
     ê²°
    -0.08
    mayacak
    -0.08
    POSITIVE LOGITS
     becomes
    0.53
     become
    0.44
    bec
    0.31
     Become
    0.31
     ÑģÑĤановиÑĤÑģÑı
    0.31
     trợ
    0.30
    åıĺå¾Ĺ
    0.29
    Become
    0.29
     became
    0.27
     menjadi
    0.27
    Activations Density 0.118%

    No Known Activations