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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23811
    Prev
    Next
    INDEX
    Explanations

    mentions of ownership or possession

    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
    vÃŃce
    -0.14
    izon
    -0.14
     Všech
    -0.14
     inh
    -0.13
    adin
    -0.13
    ì
    -0.13
     Everyday
    -0.13
    ataires
    -0.13
     Rounds
    -0.13
    rech
    -0.13
    POSITIVE LOGITS
     history
    0.28
     tendency
    0.26
     proven
    0.26
     histories
    0.26
     previously
    0.23
     History
    0.23
    -history
    0.22
     tended
    0.22
    åı²
    0.22
     previous
    0.22
    Activations Density 0.103%

    No Known Activations