© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33905
    Prev
    Next
    INDEX
    Explanations

    the geometric shapes

    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
     triangular
    -0.12
     rectangular
    -0.11
     cylindrical
    -0.10
    è£ķ
    -0.10
    Stride
    -0.10
     diagonal
    -0.09
     spherical
    -0.09
    rame
    -0.09
     Duy
    -0.09
    kelas
    -0.09
    POSITIVE LOGITS
     shapes
    0.41
     shape
    0.39
     Shape
    0.32
     Shapes
    0.32
    shapes
    0.29
    shape
    0.29
    å½¢
    0.28
    Shape
    0.28
    Shapes
    0.25
    _shape
    0.24
    Activations Density 0.145%

    No Known Activations