© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    registry entries

    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
    ToFront
    -0.11
    ẻ
    -0.10
     Kaiser
    -0.09
    ohen
    -0.09
    lyn
    -0.09
    ais
    -0.09
     unr
    -0.09
     Haram
    -0.09
     Herm
    -0.09
     Tape
    -0.09
    POSITIVE LOGITS
     registry
    0.30
     reg
    0.29
     REG
    0.27
     Reg
    0.26
     Registry
    0.26
    REG
    0.24
    registry
    0.22
    Reg
    0.22
     keys
    0.21
    .reg
    0.21
    Activations Density 0.025%

    No Known Activations