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. 23544
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or contextual placements within the text

    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
    ëį°ìĿ´íĬ¸
    -0.16
    ELEMENT
    -0.16
     someone
    -0.14
    fffffff
    -0.14
    WRAPPER
    -0.14
    มหาà¸Ļà¸Ħร
    -0.13
    someone
    -0.13
    LING
    -0.13
    imulator
    -0.13
    @qq
    -0.13
    POSITIVE LOGITS
     authority
    0.28
     authorities
    0.23
     Authority
    0.23
    authority
    0.23
     positions
    0.22
    Authority
    0.21
     attendance
    0.21
     leadership
    0.21
     Positions
    0.20
     Authorities
    0.19
    Activations Density 0.057%

    No Known Activations