© 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. 24023
    Prev
    Next
    INDEX
    Explanations

    phrases related to judicial appointments and terms of service

    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
    hire
    -0.19
    aign
    -0.18
     Hire
    -0.17
    £i
    -0.17
    igne
    -0.16
     hired
    -0.16
    -appointed
    -0.14
    izr
    -0.14
    Delegate
    -0.14
    ÑĪев
    -0.14
    POSITIVE LOGITS
     fill
    0.25
     head
    0.24
     replace
    0.24
     serve
    0.24
     positions
    0.22
     Replace
    0.22
    serve
    0.22
     fills
    0.21
     position
    0.21
     replaced
    0.20
    Activations Density 0.039%

    No Known Activations