© 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. 4323
    Prev
    Next
    INDEX
    Explanations

    koala or koala-13b

    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
    o
    -0.12
    oce
    -0.12
    eres
    -0.10
    se
    -0.10
     Maz
    -0.09
     innocent
    -0.09
    fe
    -0.09
    Ìĥ
    -0.09
    uly
    -0.09
    ben
    -0.09
    POSITIVE LOGITS
    ordinate
    0.11
    ala
    0.10
    .unwrap
    0.10
    NECT
    0.10
    tir
    0.10
    -fi
    0.09
    ordinator
    0.09
    зÑĮ
    0.09
    imeter
    0.09
    OMPI
    0.09
    Activations Density 0.035%

    No Known Activations