Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 15870
    Prev
    Next
    INDEX
    Explanations

    references to virtual reality technology and its advancements

    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
    iek
    -0.16
    itech
    -0.14
     experiment
    -0.14
     Module
    -0.14
     Harm
    -0.14
    Touches
    -0.14
    etch
    -0.13
     Ingen
    -0.13
    èµ·
    -0.13
    uft
    -0.13
    POSITIVE LOGITS
    imm
    0.23
     Imm
    0.22
    Imm
    0.20
    -imm
    0.20
     immersion
    0.19
     imm
    0.19
    immers
    0.18
    immer
    0.18
     immer
    0.17
    Reality
    0.17
    Activations Density 0.051%

    No Known Activations