© 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 EvalsExportsinterp-engineNEWAPI 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. 12743
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance technology and its implications

    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
    Rocket
    -0.17
    loh
    -0.16
    åĨ
    -0.15
    iaux
    -0.14
    коÑĤ
    -0.14
    indow
    -0.14
    eny
    -0.14
     cartoons
    -0.14
    AUDIO
    -0.14
    ãĤ¤ãĥ³ãĥĪ
    -0.14
    POSITIVE LOGITS
     camera
    0.70
     cameras
    0.65
     Camera
    0.60
     cam
    0.58
     cams
    0.55
    cam
    0.54
    -camera
    0.53
    camera
    0.53
     Cameras
    0.51
    Cam
    0.51
    Activations Density 0.071%

    No Known Activations