© 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. 37518
    Prev
    Next
    INDEX
    Explanations

    say before I say

    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
    ,､
    -0.09
    åij¼ãģ°
    -0.08
    chaft
    -0.08
    ALER
    -0.08
    arpa
    -0.08
    çļĦæīĭ
    -0.07
     recess
    -0.07
    rych
    -0.07
    idal
    -0.07
     Mickey
    -0.07
    POSITIVE LOGITS
     saying
    0.55
     say
    0.52
     SAY
    0.40
    说
    0.40
    .say
    0.40
    say
    0.39
     says
    0.39
     said
    0.39
     Say
    0.37
    Say
    0.37
    Activations Density 0.264%

    No Known Activations