© 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. 23029
    Prev
    Next
    INDEX
    Explanations

    elements related to the "My Little Pony" franchise and its characters

    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
    agogue
    -0.17
    ubu
    -0.16
    æ²ĥ
    -0.16
    ufs
    -0.15
    669
    -0.14
     Getty
    -0.14
    keley
    -0.14
    zin
    -0.14
    216
    -0.14
    quirrel
    -0.14
    POSITIVE LOGITS
     pony
    0.31
     pon
    0.30
     equ
    0.25
     Pony
    0.24
     stall
    0.24
     Rarity
    0.22
     Alic
    0.22
     Canter
    0.22
    pon
    0.21
     Pon
    0.21
    Activations Density 0.027%

    No Known Activations