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. 23315
    Prev
    Next
    INDEX
    Explanations

    references to differing opinions or perspectives, particularly in relation to social issues

    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
     hlav
    -0.14
    ¸ı
    -0.14
    .Sdk
    -0.14
    .CustomButton
    -0.14
    Âłro
    -0.14
    _aliases
    -0.13
     ÄĮer
    -0.13
    мини
    -0.13
    arges
    -0.13
    .om
    -0.12
    POSITIVE LOGITS
     across
    0.25
     among
    0.25
     there
    0.24
     overall
    0.23
     Across
    0.21
     amongst
    0.20
    Overall
    0.20
     Overall
    0.20
     Among
    0.20
    Across
    0.19
    Activations Density 0.249%

    No Known Activations