© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24689
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections in legal or investigative contexts

    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
     Thief
    -0.14
    lein
    -0.13
    antt
    -0.13
    eras
    -0.13
    mi
    -0.12
    eum
    -0.12
     appellate
    -0.12
    oux
    -0.12
     Jury
    -0.12
    inet
    -0.12
    POSITIVE LOGITS
     case
    1.02
    case
    0.80
     Case
    0.78
     cases
    0.77
    -case
    0.73
     caso
    0.71
    Case
    0.69
    _case
    0.67
    	case
    0.62
     Cases
    0.62
    Activations Density 0.108%

    No Known Activations