© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 20767
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

    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
     five
    -0.13
     seven
    -0.11
    äºĶ
    -0.10
     Morr
    -0.10
     Five
    -0.10
     Fifth
    -0.10
     eight
    -0.09
    five
    -0.09
     Newman
    -0.09
     fifth
    -0.09
    POSITIVE LOGITS
    12
    0.18
     dozen
    0.16
    åįģäºĮ
    0.16
    elfth
    0.14
    Û±Û²
    0.13
     Twelve
    0.12
     unlucky
    0.12
     XII
    0.12
    13
    0.12
    11
    0.11
    Activations Density 0.105%

    No Known Activations