© 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. 45416
    Prev
    Next
    INDEX
    Explanations

    budget constraints or planning

    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
    493
    -0.10
    cente
    -0.10
     Tir
    -0.10
    lob
    -0.09
    AZE
    -0.09
    andra
    -0.09
    ika
    -0.09
    BufferSize
    -0.09
    haf
    -0.09
    ieur
    -0.08
    POSITIVE LOGITS
    ary
    0.38
    ing
    0.27
    ARY
    0.23
    ed
    0.22
    ted
    0.20
    arily
    0.20
    ting
    0.17
     ary
    0.17
    eer
    0.15
    -friendly
    0.15
    Activations Density 0.020%

    No Known Activations