© 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. 62424
    Prev
    Next
    INDEX
    Explanations

    table column headers

    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
     addCriterion
    -0.10
    ogn
    -0.09
    <![
    -0.08
    KERNEL
    -0.08
    IEW
    -0.08
    ember
    -0.08
    onds
    -0.08
    indered
    -0.08
     pii
    -0.08
    coe
    -0.08
    POSITIVE LOGITS
    #",
    0.13
     ï¼¼
    0.11
    Sr
    0.10
     serial
    0.10
     Name
    0.10
    Nr
    0.10
    No
    0.10
    amo
    0.09
    åºı
    0.09
     ï¼¼\n
    0.09
    Activations Density 0.023%

    No Known Activations