© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8868
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to programming and technical definitions

    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
    isd
    -0.15
    antan
    -0.14
    UGIN
    -0.13
    456
    -0.13
    ilog
    -0.13
    olia
    -0.13
    orda
    -0.13
    adle
    -0.13
    ìĻķ
    -0.13
    )prepare
    -0.13
    POSITIVE LOGITS
     concept
    0.97
     concepts
    0.85
     Concept
    0.76
    concept
    0.76
     Concepts
    0.75
    Concept
    0.75
    æ¦Ĥ念
    0.70
     notion
    0.66
     notions
    0.58
     idea
    0.51
    Activations Density 0.034%

    No Known Activations