© 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. 28742
    Prev
    Next
    INDEX
    Explanations

    membership-related terms and discussions about services

    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
    owell
    -0.15
    Ñģов
    -0.14
     propag
    -0.13
    inium
    -0.13
    pon
    -0.13
    ông
    -0.13
    cul
    -0.13
    iks
    -0.13
     SPDX
    -0.12
     trunc
    -0.12
    POSITIVE LOGITS
     joined
    0.43
     Joined
    0.41
    Joined
    0.40
     join
    0.36
     Join
    0.34
    joined
    0.33
     joining
    0.32
    Join
    0.31
     JOIN
    0.28
     joins
    0.28
    Activations Density 0.001%

    No Known Activations