© 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. 29973
    Prev
    Next
    INDEX
    Explanations

    philosophical concepts related to existence and belief

    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
    icontrol
    -0.14
    æľīéĻIJ
    -0.14
    scoped
    -0.14
     Pessoa
    -0.14
    .parsers
    -0.13
    ĨĴ
    -0.13
    igen
    -0.13
    .NULL
    -0.13
    ury
    -0.13
     paradox
    -0.13
    POSITIVE LOGITS
     objective
    0.29
     Objective
    0.25
     independently
    0.25
    Objective
    0.23
    objective
    0.23
     independent
    0.23
    -independent
    0.23
     underlying
    0.23
     correspondence
    0.21
    Independent
    0.21
    Activations Density 0.037%

    No Known Activations