© 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. 35371
    Prev
    Next
    INDEX
    Explanations

    expose secrets

    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
     unl
    -0.11
     gro
    -0.09
    _Framework
    -0.09
     propaganda
    -0.09
    scription
    -0.09
     sneak
    -0.09
    Availability
    -0.09
    åĢį
    -0.09
     zaz
    -0.08
    奪
    -0.08
    POSITIVE LOGITS
     expose
    0.19
     whistle
    0.18
    Expose
    0.18
     expos
    0.17
    istle
    0.16
     exposing
    0.16
    ileaks
    0.16
     exposure
    0.15
     exposed
    0.15
    æı
    0.15
    Activations Density 0.059%

    No Known Activations