© 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. 23911
    Prev
    Next
    INDEX
    Explanations

    references to political and social criticism, particularly related to authority and media

    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
     ```↵
    -0.19
     ```
    -0.18
    ————————————————
    -0.18
     ##
    -0.16
     =================================================================
    -0.16
    .*/↵
    -0.15
     ----------------------------------------------------------------------------------------------------------------
    -0.15
    ↵
    -0.14
    !]
    -0.14
    iets
    -0.14
    POSITIVE LOGITS
    .↵↵
    0.26
    ãĢĤ↵↵
    0.24
    ".↵↵
    0.23
    ).↵↵
    0.22
    ).↵
    0.22
     .↵↵
    0.22
    '.↵↵
    0.21
    ').↵
    0.21
    ").↵↵
    0.21
    >.↵↵
    0.19
    Activations Density 0.129%

    No Known Activations