© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29195
    Prev
    Next
    INDEX
    Explanations

    references to items that can be recycled or reused

    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
     mattresses
    -0.18
     denim
    -0.17
     Carpenter
    -0.15
    rint
    -0.15
     band
    -0.15
    onso
    -0.14
     sheets
    -0.14
    uds
    -0.14
     asphalt
    -0.14
     pallet
    -0.14
    POSITIVE LOGITS
     vase
    0.33
     lamp
    0.29
     lamps
    0.29
     centerpiece
    0.25
     Lamp
    0.24
     candle
    0.23
    lamp
    0.23
     clocks
    0.22
     clock
    0.21
     figur
    0.21
    Activations Density 0.022%

    No Known Activations