© 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. 39556
    Prev
    Next
    INDEX
    Explanations

    bro, brother, friends

    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
     SOCK
    -0.10
     Singer
    -0.09
     poo
    -0.09
    ÌĤ
    -0.09
    anni
    -0.09
    bold
    -0.08
     Humph
    -0.08
     Sang
    -0.08
    hus
    -0.08
    igne
    -0.08
    POSITIVE LOGITS
     bro
    0.33
    bro
    0.24
     Bro
    0.22
    åħĦå¼Ł
    0.19
    Bro
    0.19
     Bros
    0.17
     brother
    0.17
     fam
    0.17
     broth
    0.17
     boss
    0.17
    Activations Density 0.204%

    No Known Activations