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. 31349
    Prev
    Next
    INDEX
    Explanations

    references to the future and predictions about upcoming developments

    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
    rado
    -0.14
     hết
    -0.14
     overarching
    -0.14
    ÑĥÑĪки
    -0.13
    ivities
    -0.13
    виÑī
    -0.13
    orsk
    -0.13
     fran
    -0.13
    alah
    -0.13
    .DataContext
    -0.13
    POSITIVE LOGITS
     rise
    0.29
     advent
    0.27
     future
    0.27
     need
    0.23
     world
    0.23
     next
    0.22
     ability
    0.22
     shift
    0.21
     era
    0.21
     Future
    0.21
    Activations Density 0.257%

    No Known Activations