© 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. 29471
    Prev
    Next
    INDEX
    Explanations

    discussions related to societal expectations and personal identity

    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
    ë³µ
    -0.15
    sic
    -0.13
    ائ
    -0.13
    undles
    -0.13
    lÃŃÄį
    -0.12
    ''''
    -0.12
    ëįķ
    -0.12
    sÃŃ
    -0.12
    æĥ
    -0.12
    /desktop
    -0.12
    POSITIVE LOGITS
     society
    0.26
     people
    0.23
     being
    0.23
     others
    0.20
     Society
    0.20
     societal
    0.18
     ppl
    0.18
     everyone
    0.18
     societies
    0.17
     sometimes
    0.17
    Activations Density 0.452%

    No Known Activations