© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 38116
    Prev
    Next
    INDEX
    Explanations

    feeling angry

    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
     terrified
    -0.13
     horrified
    -0.12
     alarmed
    -0.12
     panicked
    -0.12
     Terror
    -0.10
     discomfort
    -0.10
     terror
    -0.10
    ä¸įå®ī
    -0.09
     Fever
    -0.09
     remorse
    -0.09
    POSITIVE LOGITS
    æĢĴ
    0.41
     anger
    0.38
     angry
    0.29
     Ang
    0.28
     rage
    0.28
    anger
    0.27
     fury
    0.26
    Ang
    0.26
     Angry
    0.25
     righteous
    0.25
    Activations Density 0.183%

    No Known Activations