© 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. 38963
    Prev
    Next
    INDEX
    Explanations

    different aspects or represents a

    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
    ARB
    -0.09
     Holt
    -0.08
     constituent
    -0.08
    adoo
    -0.08
    tright
    -0.08
    ût
    -0.08
    ween
    -0.08
    ç£
    -0.08
     ***!\n
    -0.08
    isis
    -0.08
    POSITIVE LOGITS
     different
    0.29
    ä¸įåIJĮçļĦ
    0.23
     diferente
    0.22
    different
    0.20
     Different
    0.20
     particular
    0.19
    ä¸įåIJĮ
    0.19
     khác
    0.17
    Different
    0.17
     diferentes
    0.17
    Activations Density 0.114%

    No Known Activations