© 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. 13479
    Prev
    Next
    INDEX
    Explanations

    understand better and improve

    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
     weaker
    -0.14
     thinner
    -0.13
     slower
    -0.12
     lighter
    -0.11
    prak
    -0.10
     heavier
    -0.10
     softer
    -0.10
     poorer
    -0.10
     younger
    -0.09
    awner
    -0.09
    POSITIVE LOGITS
     better
    0.48
    better
    0.39
     improved
    0.35
     besser
    0.33
     Better
    0.33
    Better
    0.32
     лÑĥÑĩÑĪе
    0.31
     melhor
    0.31
     mejor
    0.30
     improve
    0.29
    Activations Density 0.169%

    No Known Activations