© 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. 37601
    Prev
    Next
    INDEX
    Explanations

    could be

    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
    nowrap
    -0.11
    anko
    -0.09
     CDC
    -0.09
    curacy
    -0.09
    itaire
    -0.09
     оÑĤли
    -0.08
    ázd
    -0.08
    gh
    -0.08
    .heap
    -0.08
    uis
    -0.08
    POSITIVE LOGITS
     provided
    0.11
     might
    0.11
     could
    0.11
     olabilir
    0.10
     based
    0.10
     called
    0.09
    zilla
    0.09
     voks
    0.09
    ercise
    0.09
     worth
    0.09
    Activations Density 0.050%

    No Known Activations