© 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. 39041
    Prev
    Next
    INDEX
    Explanations

    speaking or communication

    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
    uest
    -0.10
     sender
    -0.09
     renegot
    -0.09
     negotiating
    -0.08
     Sender
    -0.08
    ëģ¼
    -0.08
     åij
    -0.08
     cour
    -0.08
    akest
    -0.08
    490
    -0.08
    POSITIVE LOGITS
     spoke
    0.55
     speaking
    0.52
     speak
    0.52
     talking
    0.46
     talk
    0.46
     talked
    0.46
     spoken
    0.45
     speaks
    0.44
    talk
    0.39
     talks
    0.38
    Activations Density 0.175%

    No Known Activations