© 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. 37837
    Prev
    Next
    INDEX
    Explanations

    torture techniques chamber methods

    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
     massacre
    -0.11
     Cham
    -0.10
    ınca
    -0.09
     TU
    -0.09
     slaughtered
    -0.09
     butcher
    -0.09
     massac
    -0.09
     traged
    -0.09
     repl
    -0.09
     slaughter
    -0.08
    POSITIVE LOGITS
     torture
    0.30
     Tort
    0.24
     tort
    0.24
     TORT
    0.22
     treatment
    0.17
     pain
    0.15
     physical
    0.15
     battery
    0.14
    åĪij
    0.14
     beat
    0.13
    Activations Density 0.114%

    No Known Activations