© 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. 29548
    Prev
    Next
    INDEX
    Explanations

    references to justice and fairness issues

    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
    AndGet
    -0.14
    resh
    -0.14
    âĢ¦and
    -0.13
    вей
    -0.12
    λοÏį
    -0.12
    ullet
    -0.12
    âl
    -0.12
    ify
    -0.12
     STL
    -0.12
    GH
    -0.12
    POSITIVE LOGITS
     it
    0.37
     sondern
    0.28
     nor
    0.28
     but
    0.27
     sino
    0.27
     بÙĦÚ©Ùĩ
    0.25
     оно
    0.25
     It
    0.24
     nó
    0.23
    å®ĥ
    0.23
    Activations Density 0.101%

    No Known Activations