© 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. 29223
    Prev
    Next
    INDEX
    Explanations

    references to performance and accountability in competitive contexts

    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
     ÑģÑĤÑĢаÑħ
    -0.14
    NSURLSession
    -0.14
    orge
    -0.14
    SizeMode
    -0.14
    à¸Ľà¸ı
    -0.14
    ÙĪاز
    -0.13
    angers
    -0.13
    andal
    -0.13
     диÑĢекÑĤоÑĢ
    -0.13
    pcm
    -0.13
    POSITIVE LOGITS
    ailable
    0.17
     squ
    0.16
    ÑĨо
    0.16
    ̣
    0.15
    ustr
    0.15
    uve
    0.15
    ucc
    0.15
    สะ
    0.15
    gift
    0.14
    олоÑģ
    0.14
    Activations Density 0.035%

    No Known Activations