© 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. 3519
    Prev
    Next
    INDEX
    Explanations

    tecnologia de, to use

    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
     Brun
    -0.12
    Breadcrumb
    -0.10
    readcrumb
    -0.10
     nationality
    -0.10
     Hil
    -0.09
     pods
    -0.09
     Chaos
    -0.09
     Horse
    -0.09
     Mil
    -0.09
    icie
    -0.09
    POSITIVE LOGITS
     Progressive
    0.22
     PW
    0.16
     progressive
    0.15
     cord
    0.14
     offline
    0.13
    Progress
    0.13
     Cord
    0.13
    PW
    0.12
    离
    0.12
     deferred
    0.12
    Activations Density 0.049%

    No Known Activations