© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 28608
    Prev
    Next
    INDEX
    Explanations

    references to coaching and player decisions in sports contexts

    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
    odos
    -0.16
    ฯ
    -0.16
    erdem
    -0.15
    NetMessage
    -0.14
    iode
    -0.14
    .ascii
    -0.14
    BOSE
    -0.14
    IED
    -0.14
    brick
    -0.14
    aeper
    -0.14
    POSITIVE LOGITS
     signing
    0.33
     signed
    0.30
     sign
    0.28
     Signing
    0.26
     joining
    0.26
     join
    0.24
    Signing
    0.24
     ink
    0.24
    signed
    0.23
     landing
    0.23
    Activations Density 0.079%

    No Known Activations