© 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. 29275
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and authenticity in discourse

    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
    wap
    -0.15
     in
    -0.13
     &↵
    -0.13
     to
    -0.12
     InvalidArgumentException
    -0.12
    ily
    -0.12
    anel
    -0.12
     à¹ģละ
    -0.12
    elman
    -0.12
    quoi
    -0.12
    POSITIVE LOGITS
     folks
    0.17
    udder
    0.17
    :
    0.15
    è¡
    0.14
     ladies
    0.14
     dear
    0.14
    enance
    0.14
    ÙĪÛĮØ´
    0.14
     guys
    0.14
    rames
    0.14
    Activations Density 0.202%

    No Known Activations