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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 24836
    Prev
    Next
    INDEX
    Explanations

    past previous recent earlier

    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
     next
    -0.11
     ÑģледÑĥÑİÑī
    -0.11
     upcoming
    -0.11
    以åIJİ
    -0.10
     future
    -0.10
    ê³
    -0.09
    next
    -0.09
     successors
    -0.09
     próxima
    -0.09
     Following
    -0.09
    POSITIVE LOGITS
     past
    0.50
     previous
    0.46
     recent
    0.37
    past
    0.34
    previous
    0.34
     Previous
    0.30
    è¿ĩåİ»
    0.30
    Previous
    0.29
     earlier
    0.27
    (previous
    0.25
    Activations Density 0.193%

    No Known Activations