© 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. 32934
    Prev
    Next
    INDEX
    Explanations

    references to environmental concerns and issues related to illegal activity

    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
     Plat
    -0.15
    atus
    -0.15
    itus
    -0.15
    ìĬ¹
    -0.15
    kola
    -0.15
    elpers
    -0.14
    CRT
    -0.14
    ether
    -0.14
    addtogroup
    -0.14
    hsi
    -0.14
    POSITIVE LOGITS
     fence
    0.49
     fences
    0.44
     fencing
    0.41
     Fence
    0.38
     gate
    0.36
     gates
    0.36
     Gate
    0.33
     wire
    0.30
     Gates
    0.30
     barrier
    0.29
    Activations Density 0.036%

    No Known Activations