© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    U-Net, Relu, ReSTIR, K-means, SVD, Levenshtein

    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
    eprom
    -0.10
     Knot
    -0.09
    ekt
    -0.09
     clad
    -0.09
     eve
    -0.09
     Strand
    -0.09
     Predictor
    -0.08
     neod
    -0.08
    .Real
    -0.08
    loop
    -0.08
    POSITIVE LOGITS
    Net
    0.12
    BERT
    0.10
     Net
    0.10
    attention
    0.10
     attention
    0.10
    means
    0.10
    ouv
    0.09
    pNet
    0.09
    GAN
    0.09
    Prop
    0.09
    Activations Density 0.239%

    No Known Activations