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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41290
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to environmental tasks and game mechanics

    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
    ibar
    -0.14
    logger
    -0.14
    alted
    -0.13
    .accel
    -0.13
    ople
    -0.13
     doma
    -0.13
    _firestore
    -0.13
    urls
    -0.13
    ihan
    -0.12
    bett
    -0.12
    POSITIVE LOGITS
     enemies
    0.27
     enemy
    0.24
     objectives
    0.19
     foes
    0.16
     screen
    0.16
     Enemies
    0.15
     teammates
    0.15
     Enemy
    0.15
     areas
    0.15
     scripted
    0.15
    Activations Density 0.078%

    No Known Activations