© 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. 57903
    Prev
    Next
    INDEX
    Explanations

    to followed by an action

    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
     ensure
    -0.10
     decide
    -0.10
     Ensure
    -0.10
     ensuring
    -0.10
    .ensure
    -0.10
    iert
    -0.09
    Ensure
    -0.09
    ä¿Ŀè¯ģ
    -0.09
     Pett
    -0.09
     ensured
    -0.09
    POSITIVE LOGITS
     include
    0.11
     always
    0.11
    ffee
    0.11
     check
    0.10
    ying
    0.10
    chal
    0.09
     factor
    0.09
    always
    0.09
     toujours
    0.09
     includes
    0.09
    Activations Density 0.034%

    No Known Activations