© 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. 41898
    Prev
    Next
    INDEX
    Explanations

    mentions of baby animals

    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
    åħ½
    -0.22
     lizard
    -0.20
     Animal
    -0.17
     insect
    -0.17
    ODEV
    -0.16
     hayvan
    -0.16
     animal
    -0.15
     звеÑĢ
    -0.15
     zvÃŃÅĻ
    -0.15
     rodents
    -0.15
    POSITIVE LOGITS
     polar
    0.23
     endangered
    0.22
    izzly
    0.19
     wal
    0.18
     plat
    0.17
     sperm
    0.17
     Passenger
    0.17
     threatened
    0.17
     rh
    0.17
     Giant
    0.17
    Activations Density 0.051%

    No Known Activations