© 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. 38842
    Prev
    Next
    INDEX
    Explanations

    future or future from now

    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
    .scalablytyped
    -0.10
    -before
    -0.09
    aucoup
    -0.09
     Later
    -0.09
     Gle
    -0.09
    ä¸įæĸŃ
    -0.08
    YTE
    -0.08
     nowhere
    -0.08
    emy
    -0.08
     Jew
    -0.08
    POSITIVE LOGITS
     future
    0.35
    future
    0.28
    以åIJİ
    0.25
     futuro
    0.24
     bundan
    0.24
     moving
    0.22
     hence
    0.21
    forth
    0.20
    Future
    0.20
     Zukunft
    0.19
    Activations Density 0.210%

    No Known Activations