© 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. 10252
    Prev
    Next
    INDEX
    Explanations

    et followed by suffixes

    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
    HL
    -0.09
     Gat
    -0.09
     ::::::::
    -0.09
    âĢ¦\n\n\n
    -0.08
     Jarvis
    -0.08
    erc
    -0.08
    otta
    -0.08
    hold
    -0.08
    ham
    -0.08
    à¹Īาย
    -0.08
    POSITIVE LOGITS
    ters
    0.16
    ymology
    0.16
    ienne
    0.14
     al
    0.14
     Et
    0.14
    ched
    0.13
    .SubElement
    0.13
    udes
    0.13
    ablish
    0.13
    erna
    0.12
    Activations Density 0.041%

    No Known Activations