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. 9264
    Prev
    Next
    INDEX
    Explanations

    references to media publications and their affiliations

    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
    umer
    -0.18
    adil
    -0.16
    анÑĮ
    -0.15
    .nlm
    -0.15
    ãģĵãĤĵ
    -0.15
    enderit
    -0.14
     Nome
    -0.14
    ENCIL
    -0.14
    thood
    -0.14
     Blanc
    -0.14
    POSITIVE LOGITS
     Financial
    0.23
     daily
    0.22
     Die
    0.22
     newspaper
    0.21
     magazine
    0.21
    Financial
    0.20
     Espresso
    0.20
     Frank
    0.19
     Bild
    0.19
     Zaman
    0.19
    Activations Density 0.031%

    No Known Activations