© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    legal terminology and discussions regarding governance

    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
    strict
    -0.15
     Ready
    -0.14
     дÑĥÑħ
    -0.14
    478
    -0.14
    ÑĢава
    -0.14
    ready
    -0.14
     ready
    -0.14
     spread
    -0.14
    gon
    -0.13
    ignant
    -0.13
    POSITIVE LOGITS
     construct
    0.18
    ettes
    0.17
    with
    0.16
    ucc
    0.16
    WithError
    0.16
    without
    0.15
    ReuseIdentifier
    0.15
     compet
    0.15
    OffsetTable
    0.15
     avec
    0.15
    Activations Density 0.347%

    No Known Activations