© 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. 19926
    Prev
    Next
    INDEX
    Explanations

    creates or results in

    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
    ibel
    -0.10
     Dro
    -0.09
     Protect
    -0.09
     поба
    -0.09
     cont
    -0.09
    serve
    -0.08
    é¡ĶãĤĴ
    -0.08
     raising
    -0.08
     Performing
    -0.08
    ÑĢова
    -0.08
    POSITIVE LOGITS
     resulting
    0.22
     creates
    0.20
     tạo
    0.19
     creating
    0.18
     create
    0.17
     gives
    0.17
     giving
    0.17
     give
    0.16
     produces
    0.16
     resulted
    0.16
    Activations Density 0.247%

    No Known Activations