© 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. 24082
    Prev
    Next
    INDEX
    Explanations

    references to political processes and investigations

    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
    æļ´
    -0.15
    stanov
    -0.13
     bw
    -0.13
    izer
    -0.13
    æ½
    -0.13
    ']!='
    -0.13
    ç¸
    -0.13
    Shock
    -0.13
    ¯u
    -0.13
    INET
    -0.13
    POSITIVE LOGITS
     ongoing
    0.38
    ongo
    0.29
     current
    0.26
     situation
    0.25
     debate
    0.23
     saga
    0.22
     continuing
    0.22
     crisis
    0.21
    ngoing
    0.21
     spat
    0.21
    Activations Density 0.165%

    No Known Activations