© 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. 30149
    Prev
    Next
    INDEX
    Explanations

    references to years and notable film titles or series

    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
     Bush
    -0.27
     bush
    -0.24
    Bush
    -0.23
    ioneer
    -0.17
     bloggers
    -0.15
    ennon
    -0.15
     é«
    -0.14
    .Annotations
    -0.14
    .ua
    -0.14
    Blog
    -0.14
    POSITIVE LOGITS
    199
    0.51
     Clinton
    0.34
    Û±Û¹Û¹
    0.32
    97
    0.26
    Clinton
    0.25
     Clintons
    0.23
    98
    0.22
    96
    0.22
    95
    0.19
     Nets
    0.19
    Activations Density 0.054%

    No Known Activations