© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45240
    Prev
    Next
    INDEX
    Explanations

    network diagnostics (ping, status, timing)

    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
     Pep
    -0.09
     simul
    -0.09
    ÅĤem
    -0.09
     :/:
    -0.09
     Visible
    -0.09
    455
    -0.09
     Hog
    -0.08
     Muse
    -0.08
    pb
    -0.08
     lur
    -0.08
    POSITIVE LOGITS
     ping
    0.30
     Ping
    0.27
    ping
    0.27
    Ping
    0.26
    .ping
    0.24
    PING
    0.22
    _ping
    0.19
    pong
    0.16
     pong
    0.16
    tracer
    0.15
    Activations Density 0.068%

    No Known Activations