© 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 EvalsExportsAPI 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. 42665
    Prev
    Next
    INDEX
    Explanations

    references to performance quality and collaboration in the context of a team or cast

    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
    Å¡k
    -0.18
    iaux
    -0.17
    undry
    -0.16
    ’ÑĶ
    -0.15
     Concert
    -0.15
    AZE
    -0.15
    uala
    -0.15
    æ§
    -0.15
    èŃľ
    -0.14
    usercontent
    -0.14
    POSITIVE LOGITS
     actors
    0.82
     actor
    0.76
     cast
    0.70
     Actors
    0.63
     actress
    0.61
     Actor
    0.61
    actor
    0.59
    actors
    0.59
     casts
    0.58
     casting
    0.57
    Activations Density 0.063%

    No Known Activations