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. 23658
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical estimates related to sports analysis

    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
    paralleled
    -0.16
     mang
    -0.15
    죽
    -0.14
    InstantiationException
    -0.14
    unami
    -0.14
    ìĬ¤ë¡ľ
    -0.14
    eless
    -0.13
    deÅŁ
    -0.13
    ालत
    -0.13
    .scalablytyped
    -0.13
    POSITIVE LOGITS
     Expected
    0.20
     expected
    0.20
     outcomes
    0.17
     outcome
    0.16
     utility
    0.16
    icer
    0.16
    odel
    0.16
     pri
    0.16
     win
    0.16
    icha
    0.15
    Activations Density 0.041%

    No Known Activations