© 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. 41286
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual themes

    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
    aura
    -0.16
    ContentAlignment
    -0.15
     religious
    -0.15
    θε
    -0.14
     religions
    -0.14
    eous
    -0.14
     å¦
    -0.14
    å¦
    -0.14
     religion
    -0.14
    ESH
    -0.14
    POSITIVE LOGITS
     lit
    0.44
     Lit
    0.41
    Lit
    0.37
    lit
    0.34
     sung
    0.23
    _lit
    0.23
     Sung
    0.22
     Offices
    0.21
     Stations
    0.21
     Mass
    0.21
    Activations Density 0.023%

    No Known Activations