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. 31332
    Prev
    Next
    INDEX
    Explanations

    financial terms and economic concepts

    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
     Bitcoins
    -0.15
    _ASSUME
    -0.15
    Insn
    -0.14
    ILA
    -0.14
    ippy
    -0.14
    Criterion
    -0.14
    ะà¹ģ
    -0.14
    llum
    -0.14
    itar
    -0.14
    heimer
    -0.13
    POSITIVE LOGITS
     token
    0.32
     Token
    0.28
    token
    0.26
     tokens
    0.25
    Token
    0.24
    _token
    0.23
    oken
    0.23
    -token
    0.23
     decentralized
    0.22
    block
    0.21
    Activations Density 0.090%

    No Known Activations