© 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. 23865
    Prev
    Next
    INDEX
    Explanations

    followed by sentence continuations

    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
     initially
    -0.11
    isky
    -0.09
    loth
    -0.08
     disposition
    -0.08
    inx
    -0.08
     sice
    -0.08
    ãĤĮãģ©
    -0.08
     zwar
    -0.08
     convers
    -0.08
    ostat
    -0.08
    POSITIVE LOGITS
    æ¯ķ
    0.13
     totiž
    0.11
    \\n
    0.10
    eras
    0.10
     '((
    0.09
    amar
    0.09
     Instead
    0.09
    /non
    0.09
     instead
    0.09
     They
    0.08
    Activations Density 0.079%

    No Known Activations