© 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. 2818
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and self-reference

    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
    vard
    -0.10
    /npm
    -0.09
    iard
    -0.08
    lag
    -0.08
    itte
    -0.08
    Ħĸ
    -0.08
    /us
    -0.08
     çĿ
    -0.08
    DBG
    -0.08
    Ł
    -0.08
    POSITIVE LOGITS
     themselves
    0.34
     herself
    0.28
     himself
    0.27
     ourselves
    0.27
     siÄĻ
    0.26
     itself
    0.26
     zich
    0.24
     mình
    0.24
     yourself
    0.23
     ÑģебÑı
    0.22
    Activations Density 0.109%

    No Known Activations