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

    Neuronpedia

    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. 28816
    Prev
    Next
    INDEX
    Explanations

    phrases related to political manipulation and safeguarding liberties

    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
    _initialized
    -0.15
    ñana
    -0.14
    ruz
    -0.14
     lấy
    -0.13
    elper
    -0.13
     MetroFramework
    -0.13
    imizer
    -0.13
    reinterpret
    -0.13
    ffe
    -0.13
    istrib
    -0.13
    POSITIVE LOGITS
     created
    0.40
     creation
    0.38
     create
    0.36
     dream
    0.32
     conj
    0.32
    åĪĽå»º
    0.32
    created
    0.32
    create
    0.30
     creating
    0.30
     creates
    0.29
    Activations Density 0.096%

    No Known Activations