© 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. 2044
    Prev
    Next
    INDEX
    Explanations

    courses and attending

    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
     graduating
    -0.11
    jah
    -0.10
     Jah
    -0.10
     recru
    -0.09
     mezun
    -0.09
     SHARE
    -0.09
     appointment
    -0.09
     graduated
    -0.09
     grads
    -0.09
    grad
    -0.08
    POSITIVE LOGITS
    åıĤåĬł
    0.21
     attend
    0.20
     attending
    0.17
     attended
    0.17
     attends
    0.17
     courses
    0.16
     register
    0.16
    åıĥ
    0.16
     Courses
    0.15
    register
    0.15
    Activations Density 0.102%

    No Known Activations