© 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. 54424
    Prev
    Next
    INDEX
    Explanations

    references to celestial events or astronomical phenomena

    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
     lunch
    -0.16
     Lunch
    -0.16
     sunshine
    -0.15
     attr
    -0.14
    ÑĢел
    -0.14
     Pace
    -0.14
    άνα
    -0.14
    è¿Ľ
    -0.13
    stu
    -0.13
    landa
    -0.13
    POSITIVE LOGITS
     viewing
    0.36
     Viewing
    0.30
     observing
    0.26
     viewer
    0.23
    Viewer
    0.22
     observations
    0.22
    -view
    0.22
     Observ
    0.21
    viewer
    0.21
     witnessing
    0.21
    Activations Density 0.036%

    No Known Activations