© 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. 64303
    Prev
    Next
    INDEX
    Explanations

    gems and jewels

    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
    ingu
    -0.09
    Ð¡Ðł
    -0.09
    thal
    -0.09
    adel
    -0.09
     depr
    -0.08
     copp
    -0.08
    è¯Ŀ
    -0.08
    able
    -0.08
    uld
    -0.08
    daemon
    -0.08
    POSITIVE LOGITS
    stone
    0.16
    stones
    0.14
    throat
    0.12
    STONE
    0.12
    üt
    0.12
     Jub
    0.12
     enc
    0.11
    ry
    0.11
     ðŁĴ
    0.10
    osate
    0.10
    Activations Density 0.037%

    No Known Activations