© 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. 29643
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to ownership or relation

    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
     ******************************************************************************↵
    -0.14
     GLsizei
    -0.14
    ores
    -0.14
    à¥įदर
    -0.14
    zee
    -0.14
    iÄħ
    -0.14
    //{{
    -0.14
    imonials
    -0.14
    sterol
    -0.14
    θή
    -0.14
    POSITIVE LOGITS
     office
    0.39
    office
    0.30
     team
    0.29
     offices
    0.26
     Office
    0.25
     staff
    0.24
     predecessors
    0.23
    team
    0.23
    -office
    0.22
     teams
    0.22
    Activations Density 0.041%

    No Known Activations