Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29950
    Prev
    Next
    INDEX
    Explanations

    numerical values related to data analysis or scientific measurement

    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
    olin
    -0.15
     olsun
    -0.14
    irut
    -0.14
    rez
    -0.14
    amo
    -0.14
    edom
    -0.13
     clone
    -0.13
    UIL
    -0.13
    aver
    -0.13
    SKTOP
    -0.13
    POSITIVE LOGITS
     respectively
    0.17
     hatta
    0.16
    ãģĿãģĹãģ¦
    0.16
     ê·¸ë¦¬ê³ł
    0.15
     &
    0.15
    ỳ
    0.14
     Pessoa
    0.14
    .RequestBody
    0.14
    IEL
    0.14
    _MSB
    0.13
    Activations Density 0.107%

    No Known Activations