© 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. 9131
    Prev
    Next
    INDEX
    Explanations

    references to official statements and testimonies in legal or investigative contexts

    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
    ÅĽcie
    -0.17
    554
    -0.15
    orton
    -0.15
    +Sans
    -0.14
     Rif
    -0.14
    /Framework
    -0.14
    335
    -0.14
    æŀĿ
    -0.13
    akis
    -0.13
     carpet
    -0.13
    POSITIVE LOGITS
     PIO
    0.20
     spokesman
    0.18
     spokesperson
    0.17
    PIO
    0.17
    .LoadScene
    0.15
    zdy
    0.15
    beros
    0.14
    ën
    0.14
     poil
    0.14
    indow
    0.14
    Activations Density 0.177%

    No Known Activations