© 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. 14458
    Prev
    Next
    INDEX
    Explanations

    yes/no and true/false classifications

    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
     Shir
    -0.09
    ÃľM
    -0.09
     HRESULT
    -0.09
    noinspection
    -0.09
    enza
    -0.08
     Doub
    -0.08
     tall
    -0.08
    ÑĸлÑĮ
    -0.08
    oub
    -0.08
     ++$
    -0.08
    POSITIVE LOGITS
     yes
    0.35
     true
    0.32
    yes
    0.29
     YES
    0.29
     Yes
    0.28
    true
    0.27
    Yes
    0.27
     false
    0.24
    YES
    0.24
     TRUE
    0.22
    Activations Density 0.063%

    No Known Activations