© 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. 28954
    Prev
    Next
    INDEX
    Explanations

    concepts related to social interactions and psychological dynamics

    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
    :System
    -0.15
    ipop
    -0.15
    amil
    -0.14
    _SEG
    -0.14
    Ĥæķ°
    -0.14
    edImage
    -0.14
    andal
    -0.14
    784
    -0.14
    747
    -0.14
    okud
    -0.14
    POSITIVE LOGITS
    ization
    0.27
    ity
    0.25
    izing
    0.25
    ized
    0.23
    ize
    0.20
    ising
    0.20
    izable
    0.20
    izer
    0.19
    isation
    0.19
    izers
    0.18
    Activations Density 0.020%

    No Known Activations