© 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. 54372
    Prev
    Next
    INDEX
    Explanations

    phrases related to population growth and increases in crime or penalties

    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
    abcdefghijklmnop
    -0.15
    owie
    -0.15
    IMER
    -0.14
    iales
    -0.14
    venir
    -0.14
    ãĥ¼ãĥģ
    -0.14
    elu
    -0.14
     Haut
    -0.14
    odata
    -0.13
     Uno
    -0.13
    POSITIVE LOGITS
     doubling
    0.63
     doubled
    0.62
     doubles
    0.55
     double
    0.55
     dou
    0.55
     Dou
    0.53
     Doub
    0.50
    dou
    0.50
     Double
    0.50
    Dou
    0.48
    Activations Density 0.018%

    No Known Activations