© 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. 35370
    Prev
    Next
    INDEX
    Explanations

    filter following #

    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
    acom
    -0.10
     dred
    -0.10
    urch
    -0.10
     generate
    -0.10
     generated
    -0.09
     generates
    -0.09
    .generate
    -0.09
     âĹĦ
    -0.09
     Balk
    -0.09
    -generated
    -0.09
    POSITIVE LOGITS
     filter
    0.16
    åĬłå·¥
    0.15
     filters
    0.14
     filtering
    0.14
    è¿Ľä¸ĢæŃ¥
    0.13
    Filter
    0.13
    filter
    0.12
     Filter
    0.12
     Filters
    0.12
     parse
    0.12
    Activations Density 0.079%

    No Known Activations