© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38072
    Prev
    Next
    INDEX
    Explanations

    world superlatives

    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
    793
    -0.09
    748
    -0.09
     Clipboard
    -0.09
    cej
    -0.08
    GBK
    -0.08
    399
    -0.08
     adj
    -0.08
    819
    -0.08
     continental
    -0.08
    665
    -0.08
    POSITIVE LOGITS
     world
    0.27
     миÑĢе
    0.22
     mundo
    0.22
    ä¸ĸçķĮ
    0.21
     اÙĦعاÙĦÙħ
    0.21
     existence
    0.20
     terms
    0.19
     monde
    0.19
     ÑģвÑĸÑĤÑĸ
    0.18
     جÙĩاÙĨ
    0.17
    Activations Density 0.058%

    No Known Activations