© 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. 29143
    Prev
    Next
    INDEX
    Explanations

    descriptions of objects and their interactive properties

    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
    ëĿ¼ë§Ī
    -0.14
    ãĤĮãģ©
    -0.14
    æĿŁ
    -0.14
     SetValue
    -0.13
    defaultValue
    -0.13
     spine
    -0.12
    nock
    -0.12
    ãĥ¡ãĥ©
    -0.12
     Cousins
    -0.12
    ilon
    -0.12
    POSITIVE LOGITS
     objects
    0.88
     Objects
    0.71
     object
    0.71
    objects
    0.69
    Objects
    0.61
    object
    0.58
    _objects
    0.58
    对象
    0.58
     objetos
    0.57
    .objects
    0.56
    Activations Density 0.082%

    No Known Activations