© 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. 51701
    Prev
    Next
    INDEX
    Explanations

    injury and wounds

    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
     Kidd
    -0.10
    intr
    -0.10
     Intr
    -0.09
     Sick
    -0.09
     Nobel
    -0.08
     massacre
    -0.08
    ething
    -0.08
     tast
    -0.08
     headache
    -0.08
     UIP
    -0.08
    POSITIVE LOGITS
     injuries
    0.49
     injury
    0.46
     injured
    0.38
     Injury
    0.35
    伤
    0.32
     inj
    0.31
    juries
    0.28
    åĤ·
    0.28
     wounds
    0.27
     wounded
    0.24
    Activations Density 0.063%

    No Known Activations