© 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. 30853
    Prev
    Next
    INDEX
    Explanations

    sw words

    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
    IGO
    -0.11
    sphere
    -0.09
     conte
    -0.09
     loose
    -0.08
     Wolver
    -0.08
     virtue
    -0.08
    cons
    -0.08
     preceded
    -0.08
    inh
    -0.08
    weise
    -0.08
    POSITIVE LOGITS
     sw
    0.17
    (sw
    0.14
    /sw
    0.13
     SW
    0.13
     Sw
    0.12
    Sw
    0.12
    .sw
    0.11
    legant
    0.10
     swo
    0.10
    оÑģлав
    0.09
    Activations Density 0.091%

    No Known Activations