© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 44075
    Prev
    Next
    INDEX
    Explanations

    assistant responsesAI model turns

    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
     EX
    -0.10
    atter
    -0.10
    tha
    -0.09
     ãģı
    -0.09
     grade
    -0.09
     Sec
    -0.08
     Assistant
    -0.08
     sec
    -0.08
     Alpine
    -0.08
    UD
    -0.08
    POSITIVE LOGITS
    ardu
    0.10
    Äı
    0.10
    >>>>>>>
    0.09
    <|end_header_id|>
    0.09
    ë§IJ
    0.08
    alom
    0.08
    I
    0.08
    .Formatter
    0.08
     Vance
    0.08
    dff
    0.08
    Activations Density 0.006%

    No Known Activations