© 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. 17372
    Prev
    Next
    INDEX
    Explanations

    user behavior

    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
     searchData
    -0.10
     Personnel
    -0.09
    anmar
    -0.09
    èĻ
    -0.09
    ëŁ½
    -0.09
    ä¼Ĺ
    -0.09
    _MEMBER
    -0.08
     Everybody
    -0.08
    rens
    -0.08
    umni
    -0.08
    POSITIVE LOGITS
     users
    0.42
     user
    0.39
    çĶ¨æĪ·
    0.39
     Users
    0.30
     полÑĮзоваÑĤ
    0.29
     çĶ¨æĪ·
    0.29
     полÑĮзоваÑĤелÑı
    0.29
    user
    0.28
    users
    0.27
    Users
    0.26
    Activations Density 0.203%

    No Known Activations