© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    references to location and the concept of belonging

    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
    éĭ
    -0.17
    ape
    -0.16
    kah
    -0.15
     éģĵ
    -0.15
    ieved
    -0.14
    kke
    -0.14
    akah
    -0.14
    ãĤ¡
    -0.14
    ruž
    -0.14
    ewire
    -0.14
    POSITIVE LOGITS
     belong
    0.47
     belongs
    0.46
     belonged
    0.40
    belongs
    0.34
     belonging
    0.34
    å±ŀäºİ
    0.29
     least
    0.20
    å±ŀ
    0.20
     thuá»Ļc
    0.19
     appart
    0.19
    Activations Density 0.024%

    No Known Activations