© 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. 34422
    Prev
    Next
    INDEX
    Explanations

    your own, oneself, yourself

    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
    isha
    -0.11
    ashi
    -0.10
    onth
    -0.09
    igs
    -0.09
     Himself
    -0.09
    elts
    -0.09
     IOCTL
    -0.09
    omain
    -0.09
    barang
    -0.08
    olta
    -0.08
    POSITIVE LOGITS
     oneself
    0.51
     ones
    0.38
     Ones
    0.36
    ones
    0.28
     your
    0.27
    ä½łçļĦ
    0.21
    your
    0.21
     yourself
    0.21
    ONES
    0.21
     own
    0.19
    Activations Density 0.371%

    No Known Activations