© 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. 41882
    Prev
    Next
    INDEX
    Explanations

    phrases related to military training and video game violence

    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
    éŀ
    -0.14
    ека
    -0.14
    ault
    -0.14
    è»Ĭ
    -0.13
     Aquarium
    -0.13
    è
    -0.13
    coil
    -0.13
    ัà¸ļà¸Ľà¸£
    -0.13
    lok
    -0.13
     dilation
    -0.13
    POSITIVE LOGITS
     planes
    0.51
     plane
    0.50
     aircraft
    0.49
     flight
    0.49
     Flight
    0.43
     aviation
    0.43
     Plane
    0.43
     airplane
    0.42
     pilots
    0.42
     airplanes
    0.41
    Activations Density 0.023%

    No Known Activations