© 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. 30413
    Prev
    Next
    INDEX
    Explanations

    key trends and developments

    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
     revolving
    -0.10
    tat
    -0.09
     Lange
    -0.09
    ÑĪки
    -0.09
     contributions
    -0.09
     Mim
    -0.08
    {{{
    -0.08
    implify
    -0.08
    TouchListener
    -0.08
     spread
    -0.08
    POSITIVE LOGITS
     trends
    0.44
     trend
    0.39
     Trends
    0.35
     developments
    0.34
     Trend
    0.27
     changes
    0.26
     events
    0.25
     forces
    0.23
     factors
    0.22
     Develop
    0.21
    Activations Density 0.114%

    No Known Activations