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. 41586
    Prev
    Next
    INDEX
    Explanations

    discussions related to taxation and fiscal policy

    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
    mil
    -0.22
    mo
    -0.19
    modifiers
    -0.18
    minute
    -0.18
    markup
    -0.17
    mes
    -0.17
    ÙħØŃ
    -0.17
    modulo
    -0.16
    modifier
    -0.16
    ladu
    -0.16
    POSITIVE LOGITS
    ÂłM
    0.59
    M
    0.56
    Âłm
    0.55
    "M
    0.49
    -m
    0.46
    +m
    0.43
    _m
    0.42
    m
    0.42
     Murray
    0.40
    =m
    0.40
    Activations Density 0.017%

    No Known Activations