© 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. 13117
    Prev
    Next
    INDEX
    Explanations

    terms related to international negotiations and military conflicts

    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
    еÑĩ
    -0.17
     instant
    -0.16
    reon
    -0.16
     pharm
    -0.14
    walker
    -0.14
     Seconds
    -0.13
     tung
    -0.13
     krát
    -0.13
    ÅĤad
    -0.13
    dden
    -0.13
    POSITIVE LOGITS
     began
    0.47
     started
    0.40
     begun
    0.37
     beginning
    0.36
     begins
    0.35
     begin
    0.34
     finished
    0.34
    å¼Ģå§ĭ
    0.32
    éĸĭå§ĭ
    0.31
     starts
    0.31
    Activations Density 0.055%

    No Known Activations