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. 23535
    Prev
    Next
    INDEX
    Explanations

    references to military actions and operations against terrorist groups

    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
    allas
    -0.14
     Alive
    -0.14
     ÑĢаздел
    -0.14
    olina
    -0.14
    æīĢå±ŀ
    -0.13
    ndx
    -0.13
     Powell
    -0.13
    niž
    -0.13
    gnu
    -0.13
    868
    -0.13
    POSITIVE LOGITS
     against
    0.47
    against
    0.40
     Against
    0.40
    Against
    0.35
     gegen
    0.27
     contre
    0.25
     proti
    0.25
     tegen
    0.25
     пÑĢоÑĤи
    0.24
     ضد
    0.23
    Activations Density 0.046%

    No Known Activations