© 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. 28950
    Prev
    Next
    INDEX
    Explanations

    jug, mug, hug, fug

    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
    uw
    -0.11
    inerary
    -0.10
     ail
    -0.10
    ords
    -0.09
    gow
    -0.09
    gua
    -0.09
    ethe
    -0.09
    hope
    -0.09
    ings
    -0.09
     Weber
    -0.09
    POSITIVE LOGITS
    ger
    0.24
    GER
    0.14
    ernaut
    0.13
    geries
    0.13
    hest
    0.13
    gets
    0.13
    leich
    0.12
    itive
    0.12
    uet
    0.11
    ediÄŁi
    0.11
    Activations Density 0.042%

    No Known Activations