Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 2556
    Prev
    Next
    INDEX
    Explanations

    references to political candidates and their interactions with voters

    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
    £
    -0.17
     programme
    -0.16
     £
    -0.16
     Felix
    -0.16
    .uk
    -0.15
     Programme
    -0.15
     (£
    -0.15
    ondon
    -0.15
    .Surface
    -0.15
     inventory
    -0.15
    POSITIVE LOGITS
     Labor
    0.34
    Labor
    0.25
     Redistributions
    0.24
     NSW
    0.22
     Federal
    0.22
     federal
    0.22
     RTBU
    0.22
     Queensland
    0.21
     Victorian
    0.21
     Tas
    0.21
    Activations Density 0.027%

    No Known Activations