© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 60104
    Prev
    Next
    INDEX
    Explanations

    frequency words like every

    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
     nightly
    -0.15
     daily
    -0.15
     weekday
    -0.14
    daily
    -0.13
    Daily
    -0.12
     Daily
    -0.11
     neust
    -0.10
     اÙĦÙĬÙĪÙħ
    -0.09
    _daily
    -0.09
    ãģ¨ãģĨ
    -0.09
    POSITIVE LOGITS
     every
    0.47
     once
    0.40
    every
    0.37
     ogni
    0.31
     Every
    0.31
    once
    0.30
    æ¯ı
    0.30
    Every
    0.30
     twice
    0.29
     æ¯ı
    0.28
    Activations Density 0.108%

    No Known Activations