© 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. 55075
    Prev
    Next
    INDEX
    Explanations

    references to billionaires and individuals of significant wealth

    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
    uzzer
    -0.16
     ESP
    -0.15
    ticks
    -0.15
    ume
    -0.14
    icast
    -0.14
    zzle
    -0.14
    ctrine
    -0.14
    uant
    -0.14
     renters
    -0.13
    lotte
    -0.13
    POSITIVE LOGITS
     ty
    0.24
    hei
    0.22
    -billion
    0.20
     magn
    0.20
     philanth
    0.19
     billionaire
    0.17
     entrepreneur
    0.16
     милли
    0.16
     investor
    0.16
     businessman
    0.16
    Activations Density 0.067%

    No Known Activations