© 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. 30031
    Prev
    Next
    INDEX
    Explanations

    references to newcomers or inexperienced individuals in a specific field

    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
    δÏİ
    -0.14
    yll
    -0.14
    atomy
    -0.14
    elif
    -0.14
    gest
    -0.14
    TRAN
    -0.14
    vil
    -0.13
    ropa
    -0.13
    Ïĥμα
    -0.13
    igh
    -0.13
    POSITIVE LOGITS
    bies
    0.32
     entr
    0.30
    bie
    0.27
     comer
    0.27
    com
    0.26
     arrivals
    0.25
    -com
    0.24
    by
    0.22
    -corner
    0.22
    bee
    0.22
    Activations Density 0.034%

    No Known Activations