© 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. 30012
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their related 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
    chartInstance
    -0.17
    iber
    -0.15
    .MixedReality
    -0.14
    emean
    -0.14
    inen
    -0.14
    UNC
    -0.14
    adge
    -0.14
    loat
    -0.14
     grav
    -0.14
    inger
    -0.14
    POSITIVE LOGITS
     version
    0.39
     Version
    0.32
    version
    0.32
     versions
    0.31
    _version
    0.31
    Version
    0.31
    -version
    0.30
     notion
    0.30
     idea
    0.29
    çīĪæľ¬
    0.28
    Activations Density 0.074%

    No Known Activations