© 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. 24111
    Prev
    Next
    INDEX
    Explanations

    found dead, died, killed

    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
     ÙħشاÙĩ
    -0.09
     graveyard
    -0.09
    Damage
    -0.09
    ensa
    -0.09
     incarcerated
    -0.09
     murderous
    -0.09
     Damage
    -0.08
    è¡
    -0.08
     McCoy
    -0.08
    æĻ®
    -0.08
    POSITIVE LOGITS
     killed
    0.31
     died
    0.28
     Killed
    0.24
     dies
    0.24
    æŃ»
    0.20
     пог
    0.19
     Died
    0.18
    æŃ»äº¡
    0.16
     death
    0.16
     chết
    0.16
    Activations Density 0.123%

    No Known Activations