© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45062
    Prev
    Next
    INDEX
    Explanations

    probability of dying

    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
    çĬ¯
    -0.09
     destroyer
    -0.09
     Severity
    -0.09
    948
    -0.09
     massacre
    -0.08
    ContentSize
    -0.08
     Neb
    -0.08
     lạc
    -0.08
     massac
    -0.08
    ovice
    -0.08
    POSITIVE LOGITS
     death
    0.36
     deaths
    0.31
     mortality
    0.31
    æŃ»äº¡
    0.27
    death
    0.26
     Mort
    0.25
     Death
    0.25
    æŃ»
    0.23
    ortality
    0.22
     Deaths
    0.22
    Activations Density 0.076%

    No Known Activations