© 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. 44161
    Prev
    Next
    INDEX
    Explanations

    check and variations

    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
     certified
    -0.08
     Certified
    -0.08
     Unicorn
    -0.08
     Forecast
    -0.08
     chast
    -0.08
     Verified
    -0.08
     Recommendations
    -0.08
     Retrie
    -0.08
     retrieved
    -0.08
     Clifford
    -0.08
    POSITIVE LOGITS
     check
    0.41
     checking
    0.34
     пÑĢовеÑĢ
    0.33
    æ£ĢæŁ¥
    0.33
     checks
    0.32
    check
    0.32
     Check
    0.30
    -check
    0.29
    _check
    0.28
     kiá»ĥm
    0.28
    Activations Density 0.454%

    No Known Activations