© 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. 60058
    Prev
    Next
    INDEX
    Explanations

    making connections with people

    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
     Female
    -0.14
     female
    -0.14
    Female
    -0.13
    female
    -0.12
    åĬĽçļĦ
    -0.10
    ãĥ¾
    -0.09
    _PEER
    -0.09
     male
    -0.09
    Ĵáŀ
    -0.09
    _female
    -0.09
    POSITIVE LOGITS
     people
    0.40
    çļĦ人
    0.29
    people
    0.28
     PEOPLE
    0.25
     Menschen
    0.25
     person
    0.24
     ngÆ°á»Ŀi
    0.24
     mensen
    0.24
     People
    0.24
    People
    0.24
    Activations Density 0.218%

    No Known Activations