© 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. 21630
    Prev
    Next
    INDEX
    Explanations

    iterations of the phrase "Team Fortress" along with related content about its releases

    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
     Dagger
    -0.17
     Sword
    -0.16
    -0.15
     Scene
    -0.14
     scary
    -0.14
     Ald
    -0.14
     endurance
    -0.14
     Mist
    -0.14
     committed
    -0.14
     dagger
    -0.14
    POSITIVE LOGITS
     undermin
    0.20
    à¤Ĥà¤ļ
    0.16
    /WebAPI
    0.16
    inery
    0.16
     ttk
    0.16
     Watt
    0.16
    çĤ®
    0.16
     Operators
    0.16
    _EMIT
    0.15
    åĿĬ
    0.15
    Activations Density 0.015%

    No Known Activations