© 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. 31301
    Prev
    Next
    INDEX
    Explanations

    replace X with Y

    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
     wit
    -0.11
    wit
    -0.11
    quisite
    -0.09
     Wit
    -0.09
     intermedi
    -0.09
    onne
    -0.09
     Zem
    -0.09
    fg
    -0.09
     borne
    -0.09
     Cru
    -0.09
    POSITIVE LOGITS
     with
    0.20
     dengan
    0.17
     withString
    0.17
     vỼi
    0.17
     withObject
    0.16
    \twith
    0.16
     replaced
    0.15
     avec
    0.15
    with
    0.15
     bằng
    0.13
    Activations Density 0.064%

    No Known Activations