© 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. 55615
    Prev
    Next
    INDEX
    Explanations

    mar word start

    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
    ente
    -0.10
    i
    -0.10
    eln
    -0.10
    ihan
    -0.10
    emi
    -0.09
    ARC
    -0.09
    iatric
    -0.09
    emon
    -0.09
    ourg
    -0.09
    emer
    -0.09
    POSITIVE LOGITS
    oon
    0.12
    ubishi
    0.12
    iner
    0.11
     Mediterr
    0.11
    erialize
    0.11
    ouflage
    0.11
    ATAB
    0.11
    itorio
    0.11
    quis
    0.11
    erial
    0.11
    Activations Density 0.020%

    No Known Activations