© 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. 54106
    Prev
    Next
    INDEX
    Explanations

    elements indicating personal experiences or emotional states

    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
    aut
    -0.17
    obo
    -0.17
    issa
    -0.17
    igh
    -0.17
    overn
    -0.17
    ãĤ©
    -0.16
    allet
    -0.16
    å¸ģ
    -0.16
    DRV
    -0.16
    ith
    -0.15
    POSITIVE LOGITS
    ght
    0.21
    ÅĽmy
    0.19
    zed
    0.19
    ng
    0.19
    i
    0.17
    rvine
    0.17
    и
    0.16
    rical
    0.16
    ngen
    0.16
    keit
    0.16
    Activations Density 0.028%

    No Known Activations