© 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. 41629
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate causation or promises involving environmental influences

    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
    ANJI
    -0.14
     DISCLAIM
    -0.14
    .Undef
    -0.13
     prostituer
    -0.13
    -LAST
    -0.12
    룴
    -0.12
    DateString
    -0.12
    WithString
    -0.12
    âĺ´
    -0.12
    ãĨ
    -0.12
    POSITIVE LOGITS
    <br
    0.14
    "\↵
    0.14
    â̦↵
    0.14
     _____
    0.13
    %C
    0.13
    &gt
    0.13
    =""↵
    0.13
    ..."↵
    0.13
    &quot
    0.13
    .â̦
    0.12
    Activations Density 0.001%

    No Known Activations