© 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. 29734
    Prev
    Next
    INDEX
    Explanations

    references to receiving and the concept of acknowledgment or responses

    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
    lio
    -0.17
    reece
    -0.16
    raid
    -0.15
    x
    -0.15
    obi
    -0.14
    reason
    -0.14
    ÙĪاÙĨ
    -0.14
    ami
    -0.14
    ÑĢеб
    -0.13
    oth
    -0.13
    POSITIVE LOGITS
    /send
    0.22
    ables
    0.17
     notice
    0.17
     backlash
    0.16
    (ed
    0.16
    /store
    0.16
     permission
    0.15
    ableView
    0.15
    ivity
    0.15
     notification
    0.15
    Activations Density 0.035%

    No Known Activations