© 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. 41791
    Prev
    Next
    INDEX
    Explanations

    words or phrases that involve the concept of reliability or high quality

    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
    reb
    -0.18
    ÑĢаÑĩ
    -0.18
    oy
    -0.15
    ritt
    -0.15
    re
    -0.15
     Kare
    -0.15
    stem
    -0.14
    rej
    -0.14
    red
    -0.14
    grown
    -0.14
    POSITIVE LOGITS
     spons
    0.19
    orida
    0.19
    ality
    0.19
    becca
    0.18
    chts
    0.18
    ify
    0.17
     cord
    0.17
    entrant
    0.17
    istance
    0.17
    iew
    0.17
    Activations Density 0.084%

    No Known Activations