© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 24211
    Prev
    Next
    INDEX
    Explanations

    aspects related to narrative structure and plot development

    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
    sterol
    -0.17
    .PropTypes
    -0.16
    .geometry
    -0.15
    esub
    -0.15
    .StackTrace
    -0.14
    allery
    -0.13
    amework
    -0.13
    mares
    -0.13
    illard
    -0.13
    егоÑĢ
    -0.13
    POSITIVE LOGITS
     sudden
    0.89
     suddenly
    0.87
     Suddenly
    0.70
     abrupt
    0.64
    çªģçĦ¶
    0.63
    udden
    0.63
    uddenly
    0.58
    Suddenly
    0.57
     abruptly
    0.53
     ê°ij
    0.45
    Activations Density 0.060%

    No Known Activations