© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 15361
    Prev
    Next
    INDEX
    Explanations

    references to leadership and political support

    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
    loha
    -0.13
    Æł
    -0.12
    æ±Ĥè´Ń
    -0.12
    orny
    -0.12
    ayım
    -0.12
    onet
    -0.12
    ãİ
    -0.12
    elsen
    -0.12
    inke
    -0.11
    lingen
    -0.11
    POSITIVE LOGITS
     this
    0.54
    this
    0.51
     our
    0.50
    (this
    0.40
     THIS
    0.38
     America
    0.36
    =this
    0.36
    	this
    0.36
    [this
    0.35
    our
    0.35
    Activations Density 0.366%

    No Known Activations