© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43017
    Prev
    Next
    INDEX
    Explanations

    events happening earlier

    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
     speedy
    -0.10
     swiftly
    -0.10
     Rapid
    -0.09
    rix
    -0.09
    ï½ī
    -0.09
     Buckley
    -0.09
    idis
    -0.09
     womb
    -0.09
     Overnight
    -0.09
     dün
    -0.09
    POSITIVE LOGITS
     early
    0.50
     earlier
    0.50
    æĹ©
    0.43
     earliest
    0.42
    early
    0.42
     Earlier
    0.38
     sỼm
    0.38
     ÑĢанÑĮÑĪе
    0.37
    Earlier
    0.36
     Early
    0.35
    Activations Density 0.132%

    No Known Activations