© 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. 13553
    Prev
    Next
    INDEX
    Explanations

    width, height, 100%, 200, 500

    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
    à¸ģà¸ķ
    -0.10
    .offsetTop
    -0.10
     Lal
    -0.10
     Inflate
    -0.09
    .scrollTop
    -0.09
    è
    -0.09
    /Core
    -0.09
    Enlarge
    -0.09
     Dak
    -0.08
    mbH
    -0.08
    POSITIVE LOGITS
    100
    0.18
     auto
    0.14
    80
    0.14
    300
    0.13
    auto
    0.13
    width
    0.13
    150
    0.12
    full
    0.12
     fit
    0.12
    200
    0.12
    Activations Density 0.018%

    No Known Activations