© 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. 41734
    Prev
    Next
    INDEX
    Explanations

    specific years or dates mentioned in the text

    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
    ÑĶм
    -0.14
    Ñľ
    -0.13
    Edition
    -0.12
    tür
    -0.12
    Î
    -0.12
    ebo
    -0.12
     yans
    -0.12
    elia
    -0.12
    efined
    -0.12
    caster
    -0.11
    POSITIVE LOGITS
    197
    0.32
    196
    0.30
    195
    0.30
    198
    0.29
    199
    0.28
    194
    0.26
    193
    0.26
    192
    0.22
    191
    0.22
    201
    0.20
    Activations Density 0.255%

    No Known Activations