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

    Neuronpedia

    Jacobian LensNEW
    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. 42466
    Prev
    Next
    INDEX
    Explanations

    phrases related to product availability and features

    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
    ë£Į
    -0.17
    ezi
    -0.16
    noop
    -0.16
    arching
    -0.16
    abis
    -0.15
    antar
    -0.15
    ouv
    -0.14
    zie
    -0.14
    MBOL
    -0.14
    ledon
    -0.14
    POSITIVE LOGITS
     unofficial
    0.33
     fan
    0.32
    fan
    0.30
     mod
    0.27
     mods
    0.25
     third
    0.25
     fans
    0.25
     aftermarket
    0.25
     community
    0.25
     Fan
    0.24
    Activations Density 0.019%

    No Known Activations