© 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. 39591
    Prev
    Next
    INDEX
    Explanations

    Verilog and HLS techniques

    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
    OPSIS
    -0.10
     stir
    -0.10
     Dix
    -0.10
    _TUN
    -0.10
    åį
    -0.09
     pcm
    -0.09
    ijd
    -0.09
    luk
    -0.09
     Audrey
    -0.09
    OPY
    -0.09
    POSITIVE LOGITS
    EDA
    0.19
     Cad
    0.17
     Ver
    0.17
     Mentor
    0.16
    Ver
    0.15
    Cad
    0.15
    eda
    0.14
     Tanner
    0.14
     Design
    0.14
     Quart
    0.14
    Activations Density 0.054%

    No Known Activations