© 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. 43869
    Prev
    Next
    INDEX
    Explanations

    references to gaming mechanics and dynamics related to single-player experiences

    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
     Colomb
    -0.16
    ursed
    -0.15
     آذ
    -0.15
    punkt
    -0.15
    $MESS
    -0.14
    IDO
    -0.14
    IDGET
    -0.14
    ingo
    -0.14
    itten
    -0.14
    iez
    -0.14
    POSITIVE LOGITS
     campaign
    0.45
     Campaign
    0.40
     campaigns
    0.38
    campaign
    0.35
     single
    0.35
    Campaign
    0.35
     modes
    0.34
     mode
    0.33
     offline
    0.32
     Single
    0.32
    Activations Density 0.039%

    No Known Activations