© 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. 15690
    Prev
    Next
    INDEX
    Explanations

    references to legislative actions regarding social issues

    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
     powder
    -0.16
    BCM
    -0.15
     Plan
    -0.15
    سÙħ
    -0.15
    Plan
    -0.14
    plan
    -0.13
    ĽĪ
    -0.13
     Davies
    -0.13
     plan
    -0.13
     Grave
    -0.13
    POSITIVE LOGITS
     passed
    0.56
     passing
    0.51
     passage
    0.49
     passes
    0.45
    passed
    0.44
     Passed
    0.42
     Passing
    0.40
     Passage
    0.40
     enacted
    0.40
    -pass
    0.39
    Activations Density 0.087%

    No Known Activations