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. 31372
    Prev
    Next
    INDEX
    Explanations

    numerical data and projections related to climate change

    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
     Daly
    -0.16
    uliar
    -0.16
    óst
    -0.15
     Valerie
    -0.14
    ÐĽÐIJ
    -0.14
     hind
    -0.14
    ãĥ³ãĥIJ
    -0.14
    çģ¯
    -0.14
     Trap
    -0.14
    elson
    -0.14
    POSITIVE LOGITS
    浦
    0.16
    оÑĤоÑĢ
    0.15
    è£ķ
    0.14
    ĸ
    0.14
    mamak
    0.14
    ÑĤеÑĢн
    0.14
     misunder
    0.14
    .shell
    0.14
    etes
    0.14
     suce
    0.14
    Activations Density 0.004%

    No Known Activations