© 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. 19666
    Prev
    Next
    INDEX
    Explanations

    one place/system

    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
    ullo
    -0.10
     cháy
    -0.09
    twig
    -0.09
    _Component
    -0.09
    atürk
    -0.09
    utow
    -0.09
    ritel
    -0.09
    iren
    -0.08
     elemental
    -0.08
    kyt
    -0.08
    POSITIVE LOGITS
     single
    0.15
    /single
    0.15
     fell
    0.13
     place
    0.13
     roof
    0.13
    -single
    0.13
     entity
    0.13
     sitting
    0.12
     go
    0.12
     swo
    0.12
    Activations Density 0.083%

    No Known Activations