© 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. 29523
    Prev
    Next
    INDEX
    Explanations

    a article followed by noun

    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
    viso
    -0.11
     joker
    -0.11
    èĢħçļĦ
    -0.10
     adventurer
    -0.10
     Lover
    -0.10
    人们
    -0.10
    urette
    -0.09
     lover
    -0.09
    à¸Ķà¸ĩ
    -0.09
     |/
    -0.09
    POSITIVE LOGITS
     disappointment
    0.13
    gh
    0.13
     liability
    0.13
     threat
    0.12
    ight
    0.12
     good
    0.11
     fraud
    0.11
     failure
    0.11
     nues
    0.11
     expert
    0.11
    Activations Density 0.129%

    No Known Activations