© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    implementing abstract concepts

    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
     subroutine
    -0.11
    iker
    -0.10
     hilar
    -0.10
     Pang
    -0.10
     moss
    -0.10
    anka
    -0.09
     brow
    -0.09
     Moss
    -0.09
     shortcut
    -0.09
     count
    -0.09
    POSITIVE LOGITS
     abstract
    0.17
    æĬ½
    0.17
     ext
    0.14
     generic
    0.14
     polym
    0.13
     factory
    0.13
     Abstract
    0.13
     dispatch
    0.13
     flexible
    0.12
    abstract
    0.12
    Activations Density 0.186%

    No Known Activations