© 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. 29576
    Prev
    Next
    INDEX
    Explanations

    phrases indicating increasing trends or statistics

    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
    ponent
    -0.16
     newcomers
    -0.14
     Campos
    -0.14
    اÙĩر
    -0.13
     massaggi
    -0.13
    perienced
    -0.13
    .heroku
    -0.13
    خة
    -0.13
    _CTX
    -0.13
    аÑģÑĤи
    -0.13
    POSITIVE LOGITS
     people
    0.40
     women
    0.27
    people
    0.26
     students
    0.25
     Americans
    0.25
     parents
    0.24
     citizens
    0.24
     consumers
    0.24
    人ãģĮ
    0.23
    人们
    0.23
    Activations Density 0.280%

    No Known Activations