Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 29867
    Prev
    Next
    INDEX
    Explanations

    expressions of contemplation or deep thought

    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
     more
    -0.21
    มาà¸ģà¸ģว
    -0.18
     somewhat
    -0.17
    annel
    -0.16
    umar
    -0.15
    AGER
    -0.15
    ATIC
    -0.14
    ONTAL
    -0.14
    inalg
    -0.14
     More
    -0.14
    POSITIVE LOGITS
     about
    0.21
    /about
    0.18
    .about
    0.16
    /OR
    0.16
    about
    0.15
     Bout
    0.15
    vern
    0.15
    ément
    0.14
    ikat
    0.14
    ç´¯
    0.14
    Activations Density 0.031%

    No Known Activations