© 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. 13605
    Prev
    Next
    INDEX
    Explanations

    significant emotional experiences or milestones related to trust and connection

    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
     plá
    -0.14
    frontend
    -0.14
    ittel
    -0.13
    Forward
    -0.13
    afia
    -0.13
    rete
    -0.13
    uras
    -0.13
    celed
    -0.13
     frontend
    -0.13
    erton
    -0.13
    POSITIVE LOGITS
     back
    1.32
    back
    0.97
    -back
    0.90
     Back
    0.90
    Back
    0.88
     BACK
    0.88
    _back
    0.84
     zurück
    0.81
    .back
    0.80
     terug
    0.77
    Activations Density 0.083%

    No Known Activations