© 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. 15659
    Prev
    Next
    INDEX
    Explanations

    references to legal authorities and their offices

    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
    unma
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
     kn
    -0.13
    avra
    -0.13
    ůl
    -0.13
    èij£äºĭ
    -0.13
     pÅĻ
    -0.13
     Shadow
    -0.13
    å»·
    -0.12
    prox
    -0.12
    POSITIVE LOGITS
     office
    0.55
    office
    0.44
     Office
    0.43
    Office
    0.40
     offices
    0.39
    -office
    0.38
    _office
    0.34
    åĬŀåħ¬
    0.34
     Offices
    0.32
    .office
    0.32
    Activations Density 0.039%

    No Known Activations