© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23878
    Prev
    Next
    INDEX
    Explanations

    terms related to local governance and community issues

    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
     både
    -0.20
     either
    -0.20
     both
    -0.18
    either
    -0.15
     Either
    -0.15
     Both
    -0.15
    both
    -0.15
    Either
    -0.15
     EITHER
    -0.15
    Both
    -0.14
    POSITIVE LOGITS
     other
    0.45
     others
    0.37
    other
    0.35
    åħ¶ä»ĸ
    0.30
     altri
    0.30
    -other
    0.28
    others
    0.27
     andere
    0.27
     autres
    0.27
     дÑĢÑĥгими
    0.27
    Activations Density 0.071%

    No Known Activations