© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 32918
    Prev
    Next
    INDEX
    Explanations

    concepts related to memory types and their characteristics

    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
    imit
    -0.15
    .AddListener
    -0.14
    agra
    -0.14
    ixin
    -0.14
    edicine
    -0.14
     bond
    -0.13
    undle
    -0.13
    ilit
    -0.13
    uggest
    -0.13
    ä¸ĭ载次æķ°
    -0.12
    POSITIVE LOGITS
     thoughts
    0.47
     Thoughts
    0.40
     thought
    0.40
    thought
    0.39
    Thought
    0.38
     Thought
    0.37
     thinking
    0.34
     mental
    0.32
     THINK
    0.31
    thinking
    0.31
    Activations Density 0.077%

    No Known Activations