© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15295
    Prev
    Next
    INDEX
    Explanations

    instances of the word "we" and phrases indicating collective action or thoughts

    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
    æĪijçļĦ
    -0.14
    annon
    -0.14
    ownload
    -0.14
    rael
    -0.14
     bana
    -0.13
    å¯Į
    -0.13
    rouw
    -0.13
    ãĤ¤ãĥ«
    -0.13
    aybe
    -0.13
    utherford
    -0.13
    POSITIVE LOGITS
    're
    0.19
     hope
    0.19
     pride
    0.18
     Are
    0.18
    ’re
    0.18
     invite
    0.18
     are
    0.17
     promise
    0.17
    BSITE
    0.17
    edo
    0.17
    Activations Density 0.092%

    No Known Activations