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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23818
    Prev
    Next
    INDEX
    Explanations

    references to the character Gandalf from the "Lord of the Rings" series

    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
    874
    -0.15
    ↵↵
    -0.15
    cks
    -0.15
    tura
    -0.15
    plementation
    -0.14
    jvu
    -0.14
    onavir
    -0.14
    Atl
    -0.14
    pec
    -0.14
    uç
    -0.14
    POSITIVE LOGITS
    alf
    0.26
    hi
    0.20
    olf
    0.16
    olph
    0.16
    ий
    0.16
     Fathers
    0.16
    toi
    0.15
    phere
    0.15
    addy
    0.15
    OLF
    0.14
    Activations Density 0.004%

    No Known Activations