© 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. 41829
    Prev
    Next
    INDEX
    Explanations

    assigning data points to clusters

    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
    ãĥ¼ãĥ¼
    -0.10
    ordes
    -0.09
     ì¸
    -0.09
     Hun
    -0.09
    aju
    -0.09
     Yaz
    -0.09
    defgroup
    -0.08
     Ivanka
    -0.08
    jad
    -0.08
    dde
    -0.08
    POSITIVE LOGITS
     points
    0.23
     observations
    0.20
     Points
    0.18
     samples
    0.18
     training
    0.17
    Points
    0.17
     observation
    0.15
    points
    0.15
     examples
    0.15
     Training
    0.15
    Activations Density 0.084%

    No Known Activations