© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1298
    Prev
    Next
    INDEX
    Explanations

    to build or create

    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
     recreated
    -0.10
     premises
    -0.10
     помеÑī
    -0.08
    ettel
    -0.08
    inq
    -0.08
    SetBranch
    -0.08
     regenerated
    -0.08
    Fcn
    -0.08
    FindObject
    -0.07
     reopened
    -0.07
    POSITIVE LOGITS
     build
    0.64
     built
    0.52
     builds
    0.49
     Build
    0.48
     construction
    0.47
    建
    0.46
    build
    0.46
     building
    0.46
     xây
    0.45
    .build
    0.43
    Activations Density 0.137%

    No Known Activations