© 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 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. 43234
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions and the need for financial support in public services

    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
    飯åºĹ
    -0.16
    CRET
    -0.15
    OUNDS
    -0.15
    otate
    -0.14
    ymb
    -0.14
    ãĥ¼ãĥį
    -0.14
     Ø´Ùĩرد
    -0.14
    apikey
    -0.14
    ApiKey
    -0.14
    .ExecuteScalar
    -0.13
    POSITIVE LOGITS
     programs
    0.24
     infrastructure
    0.24
     funding
    0.23
     scholarships
    0.23
     jobs
    0.22
     investment
    0.21
     infra
    0.21
     schools
    0.21
     education
    0.20
     affordable
    0.20
    Activations Density 0.057%

    No Known Activations