Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23303
    Prev
    Next
    INDEX
    Explanations

    statistics related to job trends in specific sectors

    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
     escorte
    -0.15
    oucher
    -0.15
    yleft
    -0.14
    á»ĭnh
    -0.14
    Boundary
    -0.14
    æ±Ĥè´Ń
    -0.14
    Badge
    -0.14
    hcp
    -0.14
    Bracket
    -0.13
    uga
    -0.13
    POSITIVE LOGITS
     bank
    1.19
     banks
    1.08
     Bank
    1.03
    bank
    0.96
     Banks
    0.95
     banking
    0.95
     BANK
    0.94
    Bank
    0.92
    banks
    0.89
    _bank
    0.81
    Activations Density 0.016%

    No Known Activations