© 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. 63721
    Prev
    Next
    INDEX
    Explanations

    pure, processed, final states before products

    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
     combinations
    -0.10
     diluted
    -0.10
     EntityState
    -0.09
    _partitions
    -0.09
     fou
    -0.09
    iner
    -0.09
     Combination
    -0.09
     proportion
    -0.09
     repl
    -0.08
    arkan
    -0.08
    POSITIVE LOGITS
     product
    0.21
     material
    0.18
     samples
    0.17
     sample
    0.16
     producto
    0.15
    product
    0.14
    产åĵģ
    0.13
     produto
    0.12
     crystals
    0.12
     Product
    0.12
    Activations Density 0.013%

    No Known Activations