© 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. 22701
    Prev
    Next
    INDEX
    Explanations

    references to titles of films or notable 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
    ãĤ¤ãĤº
    -0.15
     BaseEntity
    -0.14
    ̣
    -0.14
    326
    -0.14
    lds
    -0.14
     Æ°á»Ľc
    -0.14
    ected
    -0.14
    ody
    -0.14
     wife
    -0.14
     >č↵
    -0.13
    POSITIVE LOGITS
     King
    0.27
     king
    0.25
    King
    0.22
     KING
    0.22
     prince
    0.21
     Prince
    0.21
    rani
    0.18
    Prince
    0.18
     conscience
    0.18
    ãĤŃãĥ³ãĤ°
    0.17
    Activations Density 0.053%

    No Known Activations