© 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. 2233
    Prev
    Next
    INDEX
    Explanations

    de cache

    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
     dia
    -0.10
    Bookmark
    -0.09
     cropping
    -0.09
     Furniture
    -0.09
    è¿
    -0.09
     lob
    -0.09
     Reign
    -0.09
    eos
    -0.08
     пеÑĢеб
    -0.08
     Cust
    -0.08
    POSITIVE LOGITS
     cache
    0.37
    cache
    0.32
    ç¼ĵ
    0.30
    Cache
    0.30
     Cache
    0.30
    .cache
    0.28
    _cache
    0.27
    (cache
    0.25
    -cache
    0.24
    ocache
    0.24
    Activations Density 0.050%

    No Known Activations