© 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. 26516
    Prev
    Next
    INDEX
    Explanations

    building and developing something

    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
     поба
    -0.10
     Designs
    -0.09
     reconnect
    -0.09
     Decomp
    -0.09
     Vanity
    -0.08
    StateChanged
    -0.08
     Preparation
    -0.08
     Cunning
    -0.08
    stÅĻÃŃ
    -0.08
     abre
    -0.07
    POSITIVE LOGITS
     building
    0.38
     build
    0.38
    建ç«ĭ
    0.35
    -building
    0.30
     formation
    0.30
    building
    0.30
    build
    0.29
     develop
    0.28
     builds
    0.28
     establish
    0.28
    Activations Density 0.211%

    No Known Activations