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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54133
    Prev
    Next
    INDEX
    Explanations

    phrases related to political negotiation or decision-making

    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
    batis
    -0.17
    اظ
    -0.15
    .AppSettings
    -0.14
    rikes
    -0.14
    ãĥŃãĥ¼
    -0.14
    à¥įतà¤ķ
    -0.14
    lauf
    -0.14
    duk
    -0.13
    OrElse
    -0.13
    _due
    -0.13
    POSITIVE LOGITS
     surrender
    0.48
     relinqu
    0.40
     Surre
    0.38
     surrendered
    0.37
     handing
    0.32
     forfe
    0.32
     lose
    0.29
     giveaway
    0.29
     give
    0.28
    cede
    0.28
    Activations Density 0.036%

    No Known Activations