© 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. 24631
    Prev
    Next
    INDEX
    Explanations

    myself, my, support, and accept

    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
    •GENERAL

    No Comments

    Negative Logits
     themselves
    -0.16
     Ø®ÙĪدش
    -0.16
     us
    -0.12
    /is
    -0.10
     ìŀIJ기
    -0.10
     she
    -0.10
     your
    -0.10
     their
    -0.10
     his
    -0.10
     w
    -0.10
    POSITIVE LOGITS
     myself
    0.79
     my
    0.56
    æĪijçļĦ
    0.51
     mijn
    0.44
     minha
    0.42
     tôi
    0.39
    my
    0.38
     meu
    0.38
    æĺ¯æĪij
    0.37
     meiner
    0.37
    Activations Density 0.718%

    No Known Activations