© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43879
    Prev
    Next
    INDEX
    Explanations

    created by, developed by, made by, claimed by

    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
     thrown
    -0.10
     Myst
    -0.10
    oucher
    -0.10
    ãģĤãĤĬ
    -0.09
    814
    -0.09
    agit
    -0.09
    ACY
    -0.09
    733
    -0.09
    _ascii
    -0.08
    quat
    -0.08
    POSITIVE LOGITS
     owns
    0.15
     originally
    0.12
     responsible
    0.12
     wrote
    0.12
    è´Łè´£
    0.11
     owning
    0.11
     supplies
    0.11
     controls
    0.10
     own
    0.10
    owns
    0.10
    Activations Density 0.133%

    No Known Activations