© 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. 32991
    Prev
    Next
    INDEX
    Explanations

    references to the NSA (National Security Agency) and its activities

    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
    MeasureSpec
    -0.15
    :<?
    -0.15
    ä¸Ī
    -0.15
    odel
    -0.14
    ÐĴÐIJ
    -0.14
    çĮ
    -0.14
    avra
    -0.13
    _notify
    -0.13
    AUSE
    -0.13
    CJK
    -0.13
    POSITIVE LOGITS
    (NS
    0.22
    .gov
    0.18
    IDs
    0.17
    ID
    0.16
     Edward
    0.16
    ughty
    0.16
    IA
    0.15
    Edward
    0.15
    undy
    0.15
    elige
    0.15
    Activations Density 0.011%

    No Known Activations