© 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. 24830
    Prev
    Next
    INDEX
    Explanations

    loss of self, data, or personality

    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
     Hancock
    -0.10
    isoft
    -0.09
     Halk
    -0.09
    omen
    -0.09
     hearts
    -0.09
    æĻ´
    -0.09
     Habit
    -0.09
    ضÙĬ
    -0.09
    leton
    -0.08
    UIS
    -0.08
    POSITIVE LOGITS
     control
    0.19
     resistance
    0.18
     sense
    0.18
     inhib
    0.17
     rational
    0.16
    control
    0.16
     reality
    0.15
     vol
    0.15
     agency
    0.15
     Control
    0.14
    Activations Density 0.059%

    No Known Activations