© 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. 63453
    Prev
    Next
    INDEX
    Explanations

    instances of formal recognition and speeches related to significant events and individuals

    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
    аÑĢам
    -0.16
     Dems
    -0.15
    Investigators
    -0.14
     contamin
    -0.14
    ÃĹ↵↵
    -0.14
     advisers
    -0.14
     Lover
    -0.13
    å¿ł
    -0.13
     hải
    -0.13
     DJs
    -0.13
    POSITIVE LOGITS
     Dr
    0.35
     Prof
    0.35
     Professor
    0.35
     Mrs
    0.30
    Prof
    0.29
    Dr
    0.29
     Mr
    0.28
    Professor
    0.28
    Mr
    0.27
     PROF
    0.26
    Activations Density 0.114%

    No Known Activations