© 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. 46889
    Prev
    Next
    INDEX
    Explanations

    primarily governed, permits required

    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
    rottle
    -0.08
     forks
    -0.08
    _dropout
    -0.08
    _perms
    -0.08
    Cit
    -0.08
    270
    -0.08
    æ´ŀ
    -0.08
     dose
    -0.08
     Adrian
    -0.08
     Fork
    -0.08
    POSITIVE LOGITS
     prom
    0.16
     managed
    0.14
     handled
    0.13
     according
    0.13
     governed
    0.13
     under
    0.13
     overse
    0.13
     authority
    0.12
    managed
    0.12
     cod
    0.12
    Activations Density 0.145%

    No Known Activations