© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 42989
    Prev
    Next
    INDEX
    Explanations

    recurring themes and clichéd tropes in narratives

    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
    (defvar
    -0.18
    perimental
    -0.15
    .Sockets
    -0.14
    ãĥĿãĥ¼ãĥĪ
    -0.14
    éf
    -0.14
    swer
    -0.14
    quier
    -0.14
    ï¼ģï¼ģ↵↵
    -0.14
     NSTextAlignment
    -0.13
    ycastle
    -0.13
    POSITIVE LOGITS
     c
    0.42
     clich
    0.41
     tired
    0.41
     trop
    0.40
     hack
    0.38
     Tro
    0.34
    hack
    0.34
     tro
    0.31
     trope
    0.31
     worn
    0.31
    Activations Density 0.040%

    No Known Activations