© 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. 9874
    Prev
    Next
    INDEX
    Explanations

    finding the cause

    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
     addCriterion
    -0.09
    illo
    -0.09
     repar
    -0.09
     uns
    -0.09
     Uns
    -0.08
    AZE
    -0.08
     Sink
    -0.08
    ipy
    -0.08
     Schultz
    -0.08
    ports
    -0.08
    POSITIVE LOGITS
     cause
    0.41
     causes
    0.37
     root
    0.34
    cause
    0.33
     Cause
    0.31
     source
    0.30
     causa
    0.29
     underlying
    0.28
    Cause
    0.28
     Causes
    0.28
    Activations Density 0.067%

    No Known Activations