© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 31010
    Prev
    Next
    INDEX
    Explanations

    have any questions or further requests

    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
    ILLA
    -0.10
    epam
    -0.09
     bekl
    -0.09
    ï½Ģ
    -0.09
    ones
    -0.09
    ritz
    -0.09
    dden
    -0.08
    enga
    -0.08
    obel
    -0.08
    imbus
    -0.08
    POSITIVE LOGITS
     any
    0.38
    ä»»ä½ķ
    0.26
     anymore
    0.23
     anything
    0.22
    any
    0.22
     cualquier
    0.21
     questions
    0.21
    Any
    0.19
     Any
    0.19
     further
    0.19
    Activations Density 0.010%

    No Known Activations