© 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. 54493
    Prev
    Next
    INDEX
    Explanations

    actions related to user interactions and permissions in digital 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
     without
    -0.35
    without
    -0.29
     Without
    -0.28
     WITHOUT
    -0.27
    Without
    -0.27
     so
    -0.26
    _without
    -0.22
     ohne
    -0.22
     senza
    -0.22
     enough
    -0.22
    POSITIVE LOGITS
    æīįèĥ½
    0.36
     EACH
    0.26
    æ¯ı
    0.25
     каждÑĭй
    0.25
     every
    0.25
     inorder
    0.24
     each
    0.24
    each
    0.24
     manually
    0.24
     każ
    0.24
    Activations Density 0.040%

    No Known Activations