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. 23221
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and decisions related to the judiciary

    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
     victim
    -0.15
    ifo
    -0.15
    encil
    -0.15
     Victim
    -0.15
    apol
    -0.15
    adj
    -0.14
    ario
    -0.14
     vict
    -0.14
    implify
    -0.14
     ap
    -0.14
    POSITIVE LOGITS
     chan
    0.19
     Chief
    0.17
    Chief
    0.16
    panion
    0.16
     Equity
    0.15
    oline
    0.15
    _pagination
    0.14
    rie
    0.14
    ³»
    0.14
     holdings
    0.14
    Activations Density 0.013%

    No Known Activations