© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15683
    Prev
    Next
    INDEX
    Explanations

    references to competitions and gameplay mechanics

    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
     th
    -0.14
     ne
    -0.14
    inde
    -0.14
     
    -0.14
    aken
    -0.14
    aat
    -0.14
    inth
    -0.13
     footprint
    -0.13
    ë³´
    -0.13
     k
    -0.13
    POSITIVE LOGITS
     session
    0.39
     episode
    0.28
    session
    0.27
     Session
    0.25
    -session
    0.24
     sess
    0.22
     sessions
    0.22
    _session
    0.21
     SESSION
    0.21
    Session
    0.21
    Activations Density 0.191%

    No Known Activations