© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29669
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal accountability and political conflict

    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
    ayah
    -0.13
    IPH
    -0.13
    ذÛĮر
    -0.13
    lernen
    -0.13
    üny
    -0.13
    emploi
    -0.13
    ereotype
    -0.13
     استر
    -0.13
     bạc
    -0.13
    iedo
    -0.13
    POSITIVE LOGITS
     President
    0.26
     corruption
    0.24
     Prime
    0.24
     president
    0.24
     regime
    0.24
     cabinet
    0.23
     power
    0.23
     PM
    0.23
     Corruption
    0.21
     Cabinet
    0.21
    Activations Density 0.024%

    No Known Activations