© 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. 15322
    Prev
    Next
    INDEX
    Explanations

    terms related to climate and environmental conditions

    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
    istrovstvÃŃ
    -0.19
    ccione
    -0.18
    ำ
    -0.17
    vant
    -0.15
    oined
    -0.15
    hiba
    -0.15
    alie
    -0.14
    thouse
    -0.14
     Ãĩev
    -0.14
    ÙĦاÙĨ
    -0.14
    POSITIVE LOGITS
     experienced
    0.61
     experience
    0.42
     Experienced
    0.41
     seen
    0.37
     faced
    0.36
     suffered
    0.36
     experiences
    0.34
     encountered
    0.32
    perienced
    0.32
     Experience
    0.32
    Activations Density 0.093%

    No Known Activations