© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    simple Python malware

    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
    åĵ
    -0.10
     Tarif
    -0.10
    omics
    -0.10
    ách
    -0.10
    ÑĶм
    -0.09
     Hacker
    -0.09
    chema
    -0.09
     organs
    -0.09
     misuse
    -0.09
     ï½°
    -0.08
    POSITIVE LOGITS
     Mal
    0.21
     tro
    0.19
     Tro
    0.17
    rans
    0.16
     vir
    0.16
     ransom
    0.16
     malware
    0.16
     payload
    0.16
    mal
    0.15
    Mal
    0.15
    Activations Density 0.072%

    No Known Activations