© 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. 30002
    Prev
    Next
    INDEX
    Explanations

    themes related to relationships and their complexities

    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
    ombo
    -0.17
    iji
    -0.15
    eah
    -0.14
    åĭ¢
    -0.14
    INCREMENT
    -0.14
    ello
    -0.14
    κοÏħ
    -0.13
    iae
    -0.13
    adÃŃ
    -0.13
    lyn
    -0.13
    POSITIVE LOGITS
     lasted
    0.85
     lasting
    0.81
     lasts
    0.79
     dur
    0.70
     duration
    0.69
    lasting
    0.66
     Duration
    0.63
     Dur
    0.63
    -lasting
    0.62
    duration
    0.61
    Activations Density 0.049%

    No Known Activations