© 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. 54304
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal norms and imperatives

    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
    olest
    -0.17
    ikers
    -0.15
    illard
    -0.14
    verte
    -0.14
    ailability
    -0.14
    ainless
    -0.14
     Vital
    -0.14
    宿
    -0.14
    iosis
    -0.14
    imest
    -0.14
    POSITIVE LOGITS
    ative
    0.74
    ATIVE
    0.59
    itive
    0.54
    atives
    0.51
    atively
    0.50
    ive
    0.49
    аÑĤив
    0.48
    ativ
    0.48
    ativo
    0.41
    utive
    0.40
    Activations Density 0.035%

    No Known Activations