© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35358
    Prev
    Next
    INDEX
    Explanations

    mine, ours, yours, hers

    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
     yourselves
    -0.13
    illac
    -0.11
    aben
    -0.09
     Thou
    -0.09
    aus
    -0.09
    áv
    -0.08
    chg
    -0.08
     themselves
    -0.08
    ifie
    -0.08
     beni
    -0.08
    POSITIVE LOGITS
     mine
    0.53
    mine
    0.45
    Mine
    0.44
     Mine
    0.41
     ours
    0.39
     hers
    0.34
     mines
    0.29
    èĩªå·±çļĦ
    0.29
    ours
    0.29
    OURS
    0.28
    Activations Density 0.142%

    No Known Activations