© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 51145
    Prev
    Next
    INDEX
    Explanations

    discuss or provide

    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
     conversations
    -0.29
     conversation
    -0.25
    说è¯Ŀ
    -0.22
    conversation
    -0.21
    Conversation
    -0.20
     Conversation
    -0.20
    話
    -0.19
     convers
    -0.18
     talking
    -0.18
     talks
    -0.18
    POSITIVE LOGITS
    &
    0.11
    ington
    0.11
     exchange
    0.11
     share
    0.10
     Dro
    0.10
     hear
    0.09
     sharing
    0.09
     Cement
    0.09
    cript
    0.09
     gest
    0.09
    Activations Density 0.079%

    No Known Activations