© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 55175
    Prev
    Next
    INDEX
    Explanations

    terms related to subscription services and pricing of entertainment content

    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
     Chain
    -0.16
    meli
    -0.16
    upertino
    -0.15
     Chains
    -0.15
    ãĥ¼ãĥĪ
    -0.14
    ëł
    -0.14
    üzel
    -0.14
    ichen
    -0.14
    _delegate
    -0.14
    stoff
    -0.14
    POSITIVE LOGITS
     cable
    0.37
     Cable
    0.35
     Charter
    0.27
     Comcast
    0.26
     Fiber
    0.24
     Spectrum
    0.23
     residential
    0.23
     Residential
    0.22
     Dire
    0.22
     subscribers
    0.22
    Activations Density 0.039%

    No Known Activations