© 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. 12670
    Prev
    Next
    INDEX
    Explanations

    before installing or factory reset

    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
     restarting
    -0.14
     Restart
    -0.14
     restarted
    -0.11
     reopen
    -0.11
     equ
    -0.11
    Restart
    -0.11
     reopened
    -0.11
    restart
    -0.11
     Saving
    -0.11
     reboot
    -0.10
    POSITIVE LOGITS
     factory
    0.32
     Factory
    0.29
    factory
    0.26
    Factory
    0.23
    _factory
    0.20
    .factory
    0.17
     factories
    0.17
    (factory
    0.16
     reset
    0.16
    .Factory
    0.16
    Activations Density 0.064%

    No Known Activations