© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 8979
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" and its surrounding context

    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
     closest
    -0.24
     nearest
    -0.22
     highest
    -0.19
    highest
    -0.17
    closest
    -0.17
    ãģ°ãģĭãĤĬ
    -0.15
    liest
    -0.15
     longest
    -0.14
     shortest
    -0.14
    nearest
    -0.14
    POSITIVE LOGITS
     remaining
    0.77
     rest
    0.73
     remainder
    0.66
     others
    0.64
     other
    0.60
    remaining
    0.60
     Remaining
    0.59
    åī©
    0.58
     resto
    0.56
    Remaining
    0.55
    Activations Density 0.109%

    No Known Activations