© 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. 43020
    Prev
    Next
    INDEX
    Explanations

    morphological operations / voids

    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
     нам
    -0.10
     Cart
    -0.10
    å¦
    -0.09
     Faces
    -0.09
     pii
    -0.09
    Triangles
    -0.09
    lock
    -0.09
     fold
    -0.09
    QL
    -0.08
    _ALIGN
    -0.08
    POSITIVE LOGITS
     closing
    0.18
     erosion
    0.18
     morph
    0.18
     dil
    0.17
     morphology
    0.17
     Morph
    0.17
     dilation
    0.16
    eros
    0.16
     connectivity
    0.15
     Dil
    0.15
    Activations Density 0.027%

    No Known Activations