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. 23552
    Prev
    Next
    INDEX
    Explanations

    references to death and significant dates related to it

    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
    urga
    -0.15
    ¶Į
    -0.15
    gni
    -0.14
    æ³ģ
    -0.14
    .chars
    -0.14
     bytesRead
    -0.14
    uren
    -0.14
    licht
    -0.14
    asurer
    -0.14
    ominator
    -0.13
    POSITIVE LOGITS
     aged
    0.26
     due
    0.26
     age
    0.21
     while
    0.21
    due
    0.21
     Due
    0.19
     victim
    0.19
    -aged
    0.18
    aged
    0.18
     exact
    0.18
    Activations Density 0.037%

    No Known Activations