© 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. 63853
    Prev
    Next
    INDEX
    Explanations

    phrases indicating feelings of trust and the act of sharing information or experiences

    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
    nem
    -0.17
    ÄĽk
    -0.14
    tog
    -0.14
    .Our
    -0.14
    ennon
    -0.13
    UY
    -0.13
    Mask
    -0.13
    Measure
    -0.13
    ä»ĺãģij
    -0.13
    ngr
    -0.12
    POSITIVE LOGITS
     me
    1.15
    æĪij
    0.68
     мне
    0.57
     myself
    0.56
     us
    0.56
     saya
    0.54
     менÑı
    0.52
     tôi
    0.51
     moi
    0.48
    me
    0.47
    Activations Density 0.240%

    No Known Activations