© 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. 58610
    Prev
    Next
    INDEX
    Explanations

    bus or business

    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
    eof
    -0.12
    ewan
    -0.10
    tm
    -0.10
    sWith
    -0.10
    hort
    -0.09
    istrator
    -0.09
    aneous
    -0.09
    ei
    -0.09
    hower
    -0.09
    isbury
    -0.09
    POSITIVE LOGITS
    INESS
    0.21
    queda
    0.19
    ines
    0.18
    iness
    0.17
    inness
    0.17
    load
    0.16
    (es
    0.15
    INES
    0.15
    ier
    0.15
    ãĤ±ãĥĥãĥĪ
    0.15
    Activations Density 0.029%

    No Known Activations