© 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. 49043
    Prev
    Next
    INDEX
    Explanations

    the original / ethical / concept

    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
    acon
    -0.08
     Basics
    -0.08
     piv
    -0.08
    clusion
    -0.08
     Instruments
    -0.08
    лаÑĪ
    -0.08
    éĥ¡
    -0.08
    .devices
    -0.08
    erd
    -0.08
    igers
    -0.08
    POSITIVE LOGITS
     user
    0.14
     rules
    0.12
     owner
    0.12
     users
    0.12
     bounds
    0.11
     creator
    0.11
     original
    0.10
     model
    0.10
     limitations
    0.10
    rompt
    0.10
    Activations Density 0.049%

    No Known Activations