© 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. 60801
    Prev
    Next
    INDEX
    Explanations

    powered by

    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
     powerful
    -0.12
     powering
    -0.11
    shan
    -0.11
     overpower
    -0.10
    iness
    -0.10
     powered
    -0.10
    siz
    -0.10
    earn
    -0.10
     powerhouse
    -0.10
    sWith
    -0.10
    POSITIVE LOGITS
    fully
    0.23
    lifting
    0.17
    houses
    0.17
    train
    0.14
    ful
    0.14
    -down
    0.13
    lessness
    0.12
    centage
    0.12
    FUL
    0.12
    full
    0.12
    Activations Density 0.047%

    No Known Activations