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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23612
    Prev
    Next
    INDEX
    Explanations

    quantities or numbers related to countable items or events

    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
    -Day
    -0.17
    -days
    -0.16
     mili
    -0.16
    Days
    -0.15
     Days
    -0.15
    days
    -0.14
    Day
    -0.14
    stå
    -0.14
     Weeks
    -0.14
    -hours
    -0.13
    POSITIVE LOGITS
     years
    0.40
     year
    0.29
    years
    0.27
     Jahren
    0.24
     años
    0.24
     jaar
    0.24
     года
    0.23
    year
    0.23
     Years
    0.23
    -and
    0.23
    Activations Density 0.089%

    No Known Activations