© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment or disapproval, particularly concerning familial relationships and authority figures

    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
    üt
    -0.15
     thần
    -0.14
    loff
    -0.14
    obo
    -0.14
    iid
    -0.14
    ozor
    -0.14
    æݪ
    -0.14
    uentes
    -0.14
    ãģ£ãģį
    -0.14
     Pins
    -0.14
    POSITIVE LOGITS
     approve
    0.26
     approving
    0.25
     approval
    0.24
     proud
    0.24
     approves
    0.23
     Proud
    0.22
     approvals
    0.21
    approve
    0.21
     Approval
    0.20
     himself
    0.20
    Activations Density 0.036%

    No Known Activations