© 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. 43456
    Prev
    Next
    INDEX
    Explanations

    the romantic era

    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
     Renaissance
    -0.13
    TF
    -0.11
    193
    -0.11
     Arizona
    -0.11
     Dominion
    -0.10
     Luca
    -0.10
    HEME
    -0.10
    ocom
    -0.10
     TF
    -0.09
    plnÄĽ
    -0.09
    POSITIVE LOGITS
    181
    0.45
    182
    0.40
    183
    0.33
    180
    0.29
    179
    0.28
     Napoleon
    0.26
     Romantic
    0.25
     Nap
    0.23
     Waterloo
    0.21
     Byron
    0.21
    Activations Density 0.064%

    No Known Activations