© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    temporal anchors

    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
    loha
    -0.09
    hev
    -0.09
    él
    -0.09
    ecided
    -0.09
     gì
    -0.08
     Bylo
    -0.08
    eph
    -0.08
    achu
    -0.08
    CommandLine
    -0.08
    ût
    -0.08
    POSITIVE LOGITS
     when
    0.13
     later
    0.13
     after
    0.12
     today
    0.11
     last
    0.11
     times
    0.10
    times
    0.09
     beyond
    0.09
     yesterday
    0.09
     adulthood
    0.09
    Activations Density 0.122%

    No Known Activations