© 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. 43280
    Prev
    Next
    INDEX
    Explanations

    think and act

    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
     thoughtful
    -0.15
     thoughts
    -0.14
     Thoughts
    -0.13
    æĢĿæĥ³
    -0.11
    æĢĿ
    -0.10
     thinkers
    -0.09
     æĢ
    -0.09
    ìĪ
    -0.09
    ewis
    -0.09
     fist
    -0.09
    POSITIVE LOGITS
     action
    0.11
     acción
    0.10
     actions
    0.10
    è¡Įåĭķ
    0.10
    _ACTIONS
    0.09
     deed
    0.09
     Actions
    0.09
    Actions
    0.09
     Mandal
    0.09
    ):-
    0.09
    Activations Density 0.085%

    No Known Activations