© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 29651
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments related to gratitude and deep feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pike
    -0.15
    iate
    -0.14
    UnderTest
    -0.14
    енÑģ
    -0.13
    bote
    -0.13
    طة
    -0.13
    arhus
    -0.13
    avit
    -0.13
    zo
    -0.13
     Tubes
    -0.13
    POSITIVE LOGITS
     heart
    1.21
     Heart
    1.02
     hearts
    1.00
    heart
    0.98
    Heart
    0.92
    -heart
    0.91
     Hearts
    0.80
    å¿ĥ
    0.75
     coraz
    0.69
    -hearted
    0.68
    Activations Density 0.019%

    No Known Activations