© 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. 35019
    Prev
    Next
    INDEX
    Explanations

    each specific instance

    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
    æŁIJ
    -0.09
    unga
    -0.09
    zano
    -0.09
    ilage
    -0.09
    à¥ĩशà¤ķ
    -0.09
    uan
    -0.08
    ooth
    -0.08
     facets
    -0.08
    ache
    -0.08
    aho
    -0.08
    POSITIVE LOGITS
     respective
    0.17
    /all
    0.16
     jednotliv
    0.14
    ones
    0.13
     category
    0.12
     each
    0.12
    (each
    0.12
    ãĢħ
    0.11
    ê°ģ
    0.11
     of
    0.11
    Activations Density 0.047%

    No Known Activations