© 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. 52277
    Prev
    Next
    INDEX
    Explanations

    hitta dit

    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
     kå
    -0.24
     svens
    -0.19
     kvinn
    -0.16
     kvin
    -0.15
     svensk
    -0.15
     eskort
    -0.15
     kontakte
    -0.15
     bä
    -0.14
     vår
    -0.14
     zdrav
    -0.14
    POSITIVE LOGITS
     och
    0.21
     prostituerade
    0.21
     porrf
    0.20
     lesbisk
    0.17
     dejtings
    0.15
     dejting
    0.15
     som
    0.15
     sexle
    0.15
     dejtingsaj
    0.13
     till
    0.13
    Activations Density 0.050%

    No Known Activations