© 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. 28391
    Prev
    Next
    INDEX
    Explanations

    phrases related to media portrayal and skepticism towards vaccines

    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
    .sax
    -0.15
    æĢ§
    -0.15
     à¤ħपर
    -0.14
     Paginator
    -0.14
     dorm
    -0.14
    rompt
    -0.14
    Ø´ÙĪ
    -0.14
    ooth
    -0.14
    ëĤ´
    -0.14
    .ml
    -0.14
    POSITIVE LOGITS
     vaccine
    0.27
     vaccination
    0.26
     measles
    0.26
     Vaccine
    0.24
     vaccines
    0.24
     anti
    0.24
     NVIC
    0.23
     pseud
    0.21
     Vacc
    0.21
     parents
    0.21
    Activations Density 0.066%

    No Known Activations