© 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. 1603
    Prev
    Next
    INDEX
    Explanations

    cause and instrument relations

    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
     Horizon
    -0.09
     decl
    -0.09
     pie
    -0.09
     Triple
    -0.09
     Runtime
    -0.09
     str
    -0.09
     ha
    -0.08
    Disposable
    -0.08
    ocal
    -0.08
     tender
    -0.08
    POSITIVE LOGITS
     cause
    0.10
     instrumental
    0.10
    Cause
    0.09
     instrument
    0.09
    ornment
    0.09
     Cause
    0.09
     caus
    0.09
    iky
    0.09
    perl
    0.09
    ¶Į
    0.09
    Activations Density 0.038%

    No Known Activations