© 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. 12477
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize collective power and effort

    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
    ektor
    -0.16
    ž
    -0.15
    LineStyle
    -0.15
    áte
    -0.15
    stab
    -0.14
     exploits
    -0.14
    ágina
    -0.14
    chio
    -0.14
    á»ijng
    -0.14
    ignum
    -0.14
    POSITIVE LOGITS
     abilities
    0.38
     capabilities
    0.34
     capacities
    0.32
     means
    0.32
     capacity
    0.31
     ability
    0.31
     Abilities
    0.30
    èĥ½åĬĽ
    0.29
     capability
    0.29
     Means
    0.28
    Activations Density 0.025%

    No Known Activations