© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14844
    Prev
    Next
    INDEX
    Explanations

    references to state intervention and social policies related to economics

    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
    ambre
    -0.14
    lrt
    -0.14
     Simple
    -0.14
    undi
    -0.14
    .fig
    -0.14
    esper
    -0.14
     endowed
    -0.13
     lowers
    -0.13
     seins
    -0.13
     ::
    -0.13
    POSITIVE LOGITS
     promote
    0.26
     prom
    0.23
     further
    0.23
    Prom
    0.23
     promoting
    0.22
     promotion
    0.22
     promot
    0.22
    prom
    0.22
     promotes
    0.22
     advance
    0.22
    Activations Density 0.278%

    No Known Activations