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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 63046
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and artists involved in community activities

    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
    antom
    -0.15
    leur
    -0.15
    TypeInfo
    -0.14
    SWEP
    -0.14
    aya
    -0.14
    ãĥĥãĥģ
    -0.14
     engel
    -0.13
    åıĤåĬł
    -0.13
     welcoming
    -0.13
     chests
    -0.13
    POSITIVE LOGITS
     frequent
    0.27
     use
    0.23
     uses
    0.21
     frequ
    0.20
     Use
    0.20
     gebruik
    0.20
    åįł
    0.19
    Use
    0.19
     headquartered
    0.18
     visit
    0.18
    Activations Density 0.025%

    No Known Activations