© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35642
    Prev
    Next
    INDEX
    Explanations

    poetry slams and love of poetry

    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
     pian
    -0.10
     Dost
    -0.10
     kart
    -0.10
     histor
    -0.09
     memoir
    -0.09
    ucher
    -0.09
     prose
    -0.09
    å¥ı
    -0.09
    aroo
    -0.09
    ipro
    -0.09
    POSITIVE LOGITS
     Po
    0.30
    Po
    0.29
    po
    0.27
    è¯Ĺ
    0.27
     poems
    0.27
     poet
    0.26
     poets
    0.26
     poetry
    0.25
    _po
    0.24
    è©©
    0.24
    Activations Density 0.129%

    No Known Activations