© 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. 24046
    Prev
    Next
    INDEX
    Explanations

    references to changes, decisions, and issues related to governance, investigations, and policies

    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
     such
    -0.20
    such
    -0.15
    unei
    -0.14
    TexParameter
    -0.14
     like
    -0.13
     similarly
    -0.13
    iá»ĥn
    -0.13
    ısıt
    -0.13
    ·
    -0.13
    è¿Ļæł·çļĦ
    -0.12
    POSITIVE LOGITS
     itself
    0.22
    åıĬåħ¶
    0.20
     himself
    0.15
    oucher
    0.15
    iest
    0.14
    aviest
    0.14
     themselves
    0.14
    ãģŁãģ¡
    0.14
    .tc
    0.14
    ú
    0.14
    Activations Density 0.360%

    No Known Activations