© 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. 29999
    Prev
    Next
    INDEX
    Explanations

    concepts related to social and economic structures, particularly struggles and systems

    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
    icari
    -0.16
    abant
    -0.15
    ego
    -0.15
     çķĻ
    -0.15
    omik
    -0.14
    à¸Ļ
    -0.14
    наÑĩе
    -0.14
    _HOOK
    -0.13
    REA
    -0.13
    ìĿ´ë¹Ħ
    -0.13
    POSITIVE LOGITS
     innate
    0.21
     inherent
    0.20
     superior
    0.19
     naturally
    0.18
     Inn
    0.17
     intrinsic
    0.17
     somehow
    0.17
     unit
    0.17
     bene
    0.16
     necessarily
    0.16
    Activations Density 0.126%

    No Known Activations