© 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. 241
    Prev
    Next
    INDEX
    Explanations

    convolution, impulse, delta, lag

    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
    agy
    -0.10
     rou
    -0.10
    _slope
    -0.10
    #
    -0.09
    enos
    -0.09
    éĿ
    -0.09
     outr
    -0.09
     refriger
    -0.09
     Frequ
    -0.09
     taxable
    -0.09
    POSITIVE LOGITS
     impulse
    0.21
     convolution
    0.20
     conv
    0.20
     delta
    0.18
     Conv
    0.17
     Dir
    0.17
     dir
    0.16
    Conv
    0.16
    conv
    0.16
     impulses
    0.15
    Activations Density 0.054%

    No Known Activations