© 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. 56728
    Prev
    Next
    INDEX
    Explanations

    small dinghies or oars

    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
     snork
    -0.11
     underwater
    -0.11
     Dive
    -0.10
     biking
    -0.10
     cycling
    -0.10
     Cycling
    -0.10
     Swimming
    -0.10
     swimming
    -0.10
     kite
    -0.10
     Sailor
    -0.10
    POSITIVE LOGITS
     row
    0.40
     Row
    0.29
    -row
    0.27
    row
    0.26
    Row
    0.26
    åĪĴ
    0.25
     paddle
    0.24
    (row
    0.24
     padd
    0.23
    _row
    0.22
    Activations Density 0.067%

    No Known Activations