© 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. 24687
    Prev
    Next
    INDEX
    Explanations

    identify patterns

    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
    enen
    -0.09
     Strap
    -0.09
     kn
    -0.09
    ëĤĺ무
    -0.08
    Variant
    -0.08
    _layers
    -0.08
     Tango
    -0.08
     Baron
    -0.08
     pinpoint
    -0.08
    inth
    -0.08
    POSITIVE LOGITS
     patterns
    0.66
     pattern
    0.65
     Patterns
    0.56
    pattern
    0.53
     Pattern
    0.52
    patterns
    0.52
    Patterns
    0.48
    Pattern
    0.46
    -pattern
    0.45
    _pattern
    0.44
    Activations Density 0.121%

    No Known Activations