© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 33067
    Prev
    Next
    INDEX
    Explanations

    themes related to promises and commitments, particularly in a religious or cultural context

    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
    å²Ĺ
    -0.14
    IBOutlet
    -0.14
    rez
    -0.13
     sno
    -0.13
    jab
    -0.13
    utas
    -0.13
    æı®
    -0.13
     yard
    -0.13
    gh
    -0.13
    rc
    -0.13
    POSITIVE LOGITS
     Gad
    0.18
     hatta
    0.17
    \Php
    0.16
     Mig
    0.16
     Cush
    0.15
    اÙĥÙĨ
    0.15
    .DAO
    0.14
     Pek
    0.14
     Rarity
    0.14
     Authorized
    0.14
    Activations Density 0.110%

    No Known Activations