© 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. 30173
    Prev
    Next
    INDEX
    Explanations

    piperazine piperidine

    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
    odus
    -0.11
    ses
    -0.11
    alus
    -0.11
    sh
    -0.09
     Miner
    -0.09
    sel
    -0.09
    shi
    -0.09
    shell
    -0.09
    odom
    -0.09
    rna
    -0.09
    POSITIVE LOGITS
     Piper
    0.14
    azine
    0.13
    formance
    0.13
    idine
    0.12
     pipe
    0.12
    .pipe
    0.11
    (pipe
    0.11
     pip
    0.11
     Pipe
    0.11
    pipe
    0.11
    Activations Density 0.033%

    No Known Activations