© 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. 197
    Prev
    Next
    INDEX
    Explanations

    discipline, sword, name, receiving, brave

    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
    866
    -0.10
     riot
    -0.09
     stunned
    -0.09
    azen
    -0.09
    bung
    -0.08
     Pis
    -0.08
    à¸Ĩ
    -0.08
    é³´
    -0.08
     Globe
    -0.08
     shoot
    -0.08
    POSITIVE LOGITS
     wrath
    0.23
     ire
    0.18
     full
    0.17
     Wrath
    0.16
     consequences
    0.16
    æĢĴ
    0.16
    ocity
    0.15
     force
    0.14
    full
    0.14
     fury
    0.13
    Activations Density 0.052%

    No Known Activations