© 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. 61476
    Prev
    Next
    INDEX
    Explanations

    interrupting or coitus

    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
    enser
    -0.09
     depletion
    -0.09
    istant
    -0.09
    abcdef
    -0.09
    bine
    -0.09
    atoon
    -0.08
     xor
    -0.08
     cracks
    -0.08
     disob
    -0.08
    CLOSE
    -0.08
    POSITIVE LOGITS
     interrupt
    0.41
    interrupt
    0.40
     Interrupt
    0.38
     interrupted
    0.38
    Interrupt
    0.38
     interruption
    0.37
     interrupts
    0.36
     inter
    0.35
     INTERRU
    0.32
     Interr
    0.32
    Activations Density 0.093%

    No Known Activations