© 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. 33133
    Prev
    Next
    INDEX
    Explanations

    terms related to economic theories and social critiques, particularly those involving laissez-faire policies and their implications

    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
    ıt
    -0.13
     Lag
    -0.13
    ียà¸Ķ
    -0.13
    atta
    -0.13
     âģ
    -0.13
    rita
    -0.12
     Invalidate
    -0.12
    iator
    -0.12
     counterpart
    -0.12
    ouro
    -0.12
    POSITIVE LOGITS
     syndrome
    0.21
    atism
    0.20
     culture
    0.20
     model
    0.20
     mentality
    0.20
    ism
    0.20
    å¼ı
    0.18
     approach
    0.18
    ivism
    0.17
     Syndrome
    0.17
    Activations Density 0.712%

    No Known Activations