© 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. 41315
    Prev
    Next
    INDEX
    Explanations

    terms related to decision-making and options

    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
    ç¿°
    -0.17
    ære
    -0.15
    ClientRect
    -0.15
    ัà¸Ĺ
    -0.15
    uhn
    -0.14
    cona
    -0.14
    ospel
    -0.13
    udas
    -0.13
    odb
    -0.13
    ":[{↵
    -0.13
    POSITIVE LOGITS
     still
    1.31
     Still
    1.17
    still
    1.16
    Still
    1.12
     STILL
    1.07
     ainda
    0.75
    ä»į
    0.73
     ancora
    0.72
     masih
    0.67
    è¿ĺæĺ¯
    0.64
    Activations Density 0.125%

    No Known Activations