© 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. 35000
    Prev
    Next
    INDEX
    Explanations

    given, specific, desired, relevant, appropriate, specified, possible, corresponding

    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
    .Formatter
    -0.10
    aeda
    -0.09
    kaar
    -0.08
    059
    -0.08
    avs
    -0.08
    .mongodb
    -0.08
    orent
    -0.08
    åħ¨éĿ¢
    -0.08
    pedia
    -0.08
    finity
    -0.08
    POSITIVE LOGITS
     Blitz
    0.09
     Voll
    0.08
    uth
    0.08
    HC
    0.08
     Rag
    0.08
    laÅŁ
    0.08
     zag
    0.08
     slee
    0.07
    rag
    0.07
    oder
    0.07
    Activations Density 0.083%

    No Known Activations