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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38875
    Prev
    Next
    INDEX
    Explanations

    linking words and phrases

    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
     dva
    -0.12
     многие
    -0.12
     initials
    -0.11
     dvÄĽ
    -0.10
    евÑĭе
    -0.10
    ady
    -0.10
     неболÑĮ
    -0.10
     stakes
    -0.10
     Guidelines
    -0.10
     Scriptures
    -0.10
    POSITIVE LOGITS
     stuff
    0.21
     legislation
    0.16
     footage
    0.16
     evidence
    0.15
     gente
    0.14
     Stuff
    0.14
     advice
    0.14
    stuff
    0.14
     Legislation
    0.13
     information
    0.13
    Activations Density 0.271%

    No Known Activations