© 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. 24072
    Prev
    Next
    INDEX
    Explanations

    references to political entities and governance

    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
    à¹Ģลย
    -0.16
     eventually
    -0.16
    ãĤ¤ãĤº
    -0.15
     therefore
    -0.15
    à¹Īà¸Ńม
    -0.14
     dès
    -0.14
    rief
    -0.14
    lacak
    -0.14
     donc
    -0.14
    Brief
    -0.14
    POSITIVE LOGITS
     continue
    0.44
     continues
    0.44
    continue
    0.35
     continued
    0.34
     continuing
    0.32
     continu
    0.30
     remains
    0.30
    contin
    0.30
    	continue
    0.30
    Continue
    0.28
    Activations Density 0.035%

    No Known Activations