© 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. 41682
    Prev
    Next
    INDEX
    Explanations

    mentions of digital rights management (DRM) and related technical jargon in the context of technology and media

    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
    ECTOR
    -0.22
    E
    -0.21
    T
    -0.18
    دÙĪد
    -0.17
    ANNEL
    -0.17
    aires
    -0.17
    form
    -0.16
    ARRIER
    -0.16
    ame
    -0.16
    L
    -0.16
    POSITIVE LOGITS
    s
    0.37
    aaS
    0.25
    /OR
    0.25
    'er
    0.20
    sWith
    0.20
    senal
    0.19
    sand
    0.19
    sian
    0.18
    sut
    0.18
    /DD
    0.18
    Activations Density 2.415%

    No Known Activations