© 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. 30467
    Prev
    Next
    INDEX
    Explanations

    take and bring

    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
     Dump
    -0.11
     dumping
    -0.11
     dumps
    -0.10
    Dump
    -0.10
     dump
    -0.10
     dumped
    -0.10
    dump
    -0.09
    ablish
    -0.09
    Thrown
    -0.09
     Drop
    -0.09
    POSITIVE LOGITS
     take
    0.35
     taking
    0.29
    take
    0.28
    åıĸ
    0.27
     takeaway
    0.27
     carry
    0.27
    .take
    0.27
     took
    0.26
     Take
    0.26
     TAKE
    0.26
    Activations Density 0.103%

    No Known Activations