© 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. 2331
    Prev
    Next
    INDEX
    Explanations

    my possessive pronoun

    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
    rans
    -0.10
     fet
    -0.09
     Gong
    -0.09
     verg
    -0.09
    plr
    -0.09
     Grad
    -0.09
     cons
    -0.09
    ê°ij
    -0.09
     totally
    -0.09
     sup
    -0.08
    POSITIVE LOGITS
     my
    0.18
    æĪijçļĦ
    0.17
     myself
    0.16
     tôi
    0.16
     minha
    0.15
    让æĪij
    0.15
     meu
    0.15
    ï¼ĮæĪij
    0.14
    æĺ¯æĪij
    0.14
    æĪij
    0.14
    Activations Density 0.092%

    No Known Activations