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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23471
    Prev
    Next
    INDEX
    Explanations

    instances of factual statements or claims

    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
     therefore
    -0.17
    thus
    -0.17
     thus
    -0.16
    же
    -0.15
    Therefore
    -0.14
    次
    -0.13
    UTE
    -0.13
     à¤ĩसल
    -0.13
    oven
    -0.13
    vens
    -0.13
    POSITIVE LOGITS
     according
    0.30
     According
    0.28
     à¤ĩसम
    0.25
    According
    0.24
    according
    0.23
     here
    0.23
    åħ¶ä¸Ń
    0.23
    该
    0.23
     Among
    0.22
     therein
    0.22
    Activations Density 0.116%

    No Known Activations