© 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. 57454
    Prev
    Next
    INDEX
    Explanations

    experiencing headaches

    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
     indign
    -0.09
     DK
    -0.09
    kker
    -0.09
    ered
    -0.09
    cul
    -0.09
    lung
    -0.09
     payloads
    -0.08
    /gcc
    -0.08
    itoris
    -0.08
     irrit
    -0.08
    POSITIVE LOGITS
     headache
    0.25
     Head
    0.25
     headaches
    0.25
    头
    0.24
    -head
    0.23
    éłŃ
    0.23
     HEAD
    0.23
    aches
    0.22
    Head
    0.21
     голов
    0.21
    Activations Density 0.091%

    No Known Activations