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. 31344
    Prev
    Next
    INDEX
    Explanations

    references to individuals named Wendy or Cindy

    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
    raq
    -0.19
    /screen
    -0.15
    ırak
    -0.15
    ilde
    -0.15
    iana
    -0.15
    stin
    -0.15
    vard
    -0.14
    ave
    -0.14
    ltra
    -0.14
    anje
    -0.14
    POSITIVE LOGITS
    bags
    0.15
    uzu
    0.14
    ayout
    0.14
    akov
    0.14
    boss
    0.14
    rient
    0.14
    ocaust
    0.14
    ancellor
    0.14
    _firestore
    0.14
    иÑĤÑĥ
    0.14
    Activations Density 0.004%

    No Known Activations