© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 54478
    Prev
    Next
    INDEX
    Explanations

    phrases indicating age and personal development

    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
    ingles
    -0.17
    gram
    -0.17
    ani
    -0.16
     Gos
    -0.15
    hra
    -0.15
    oui
    -0.14
    rotch
    -0.14
    mes
    -0.14
    ANI
    -0.14
    andas
    -0.14
    POSITIVE LOGITS
     Coming
    0.35
     passage
    0.35
     coming
    0.34
     passages
    0.32
     Passage
    0.31
    Coming
    0.31
    coming
    0.29
     initiation
    0.21
     transition
    0.21
     Init
    0.21
    Activations Density 0.009%

    No Known Activations