Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23175
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships, responsibility, and social connections

    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
    oose
    -0.15
    zia
    -0.15
    ansom
    -0.15
    itto
    -0.14
    ivot
    -0.14
    erece
    -0.14
    еÑģÑĤва
    -0.13
    ière
    -0.13
    kaar
    -0.13
    ¥IJ
    -0.13
    POSITIVE LOGITS
     neighbor
    0.85
     neighbors
    0.84
    neighbor
    0.77
     neighbour
    0.76
     neighbours
    0.76
     Neighbor
    0.69
     neighborhood
    0.68
    neighbors
    0.68
    Neighbor
    0.66
     neigh
    0.64
    Activations Density 0.029%

    No Known Activations