© 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. 25319
    Prev
    Next
    INDEX
    Explanations

    Are there any injured

    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
     desperation
    -0.11
     neat
    -0.10
    resh
    -0.09
    DMI
    -0.09
    FLT
    -0.09
    絶
    -0.09
     Cort
    -0.08
    benh
    -0.08
    eniable
    -0.08
    ä¸ĭåİ»
    -0.08
    POSITIVE LOGITS
     safe
    0.18
     injuries
    0.17
    à¸Ľà¸¥à¸Ńà¸Ķà¸ł
    0.16
     shaken
    0.16
     safety
    0.16
     harm
    0.16
     alive
    0.15
     escaped
    0.15
     injury
    0.15
    å®īåħ¨
    0.15
    Activations Density 0.043%

    No Known Activations