© 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. 14406
    Prev
    Next
    INDEX
    Explanations

    read mode, rgb format, red color, root user

    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
    ",__
    -0.09
    pter
    -0.09
    rut
    -0.09
    :::::
    -0.08
     provision
    -0.08
    952
    -0.08
    /or
    -0.08
     pBuffer
    -0.08
     Guil
    -0.08
    ãĤĿ
    -0.08
    POSITIVE LOGITS
     mode
    0.11
    (default
    0.10
     vá»
    0.10
    以å¤ĸ
    0.09
    _IRQn
    0.09
    ëĿ¼ëĬĶ
    0.08
     Activate
    0.08
    OID
    0.08
     flag
    0.08
     Latter
    0.08
    Activations Density 0.116%

    No Known Activations