© 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. 9018
    Prev
    Next
    INDEX
    Explanations

    terms related to economic conditions and monetary policy

    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
    ider
    -0.14
    leh
    -0.13
    .googleapis
    -0.13
    IDER
    -0.13
    undra
    -0.13
    umn
    -0.13
    §
    -0.13
     scratched
    -0.13
    íĸ¥
    -0.13
    iec
    -0.13
    POSITIVE LOGITS
     inflation
    0.71
    flation
    0.60
     infl
    0.47
     inflate
    0.43
     def
    0.42
    inflate
    0.41
     Inflate
    0.40
    .inflate
    0.37
     inflammation
    0.36
     deflate
    0.34
    Activations Density 0.036%

    No Known Activations