© 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. 60854
    Prev
    Next
    INDEX
    Explanations

    last 1 month

    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
     pres
    -0.09
     knob
    -0.09
    koa
    -0.09
    ayas
    -0.09
     Colony
    -0.09
     versch
    -0.08
     Huss
    -0.08
     enc
    -0.08
     Swansea
    -0.08
     disability
    -0.08
    POSITIVE LOGITS
     stream
    0.19
     Stream
    0.17
    Stream
    0.15
    (stream
    0.15
    stream
    0.14
    (Stream
    0.14
    .window
    0.13
    .Stream
    0.13
     window
    0.13
     ìĬ¤íĬ¸
    0.13
    Activations Density 0.030%

    No Known Activations