© 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. 32911
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial opportunities and legal discussions

    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
     esto
    -0.15
    (getClass
    -0.15
     getClass
    -0.14
     Esto
    -0.14
    bstract
    -0.14
    aminer
    -0.14
    strand
    -0.14
     à¤ĩसà¤ķ
    -0.13
    .TabControl
    -0.13
     à¤ĩसम
    -0.13
    POSITIVE LOGITS
     those
    0.82
     that
    0.70
    those
    0.69
     Those
    0.68
    Those
    0.65
     THAT
    0.65
     That
    0.64
    That
    0.59
    éĤ£ä¸ª
    0.58
     Äijó
    0.57
    Activations Density 0.195%

    No Known Activations