© 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. 33736
    Prev
    Next
    INDEX
    Explanations

    ноÑģÑĤи ÑĤÑĢанÑģ

    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
     Huffman
    -0.10
    icked
    -0.10
     Brend
    -0.09
     bod
    -0.09
    upe
    -0.09
     styling
    -0.09
     port
    -0.09
     Tec
    -0.08
     Turing
    -0.08
    ŀ
    -0.08
    POSITIVE LOGITS
     Distribution
    0.16
     bus
    0.15
     GIS
    0.14
    Distribution
    0.14
     distribution
    0.14
     buses
    0.14
     subst
    0.14
    æ½®
    0.13
     traction
    0.13
     thy
    0.13
    Activations Density 0.053%

    No Known Activations