© 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. 1342
    Prev
    Next
    INDEX
    Explanations

    dangerous criminals, bring justice

    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
    奪
    -0.12
     murdered
    -0.12
    victim
    -0.11
     victim
    -0.11
    ophobic
    -0.10
     jail
    -0.10
     incarceration
    -0.10
    ãĢĢï¾ī
    -0.10
     attack
    -0.10
     incarcer
    -0.10
    POSITIVE LOGITS
     suspects
    0.20
     fel
    0.19
     suspected
    0.19
     accused
    0.18
     serial
    0.16
     fug
    0.16
     hardened
    0.16
     suspect
    0.16
     wanted
    0.16
     criminals
    0.16
    Activations Density 0.146%

    No Known Activations