© 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. 54429
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance and monitoring technology

    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
    abo
    -0.15
    izmet
    -0.15
    unsch
    -0.14
    abei
    -0.14
    .isDefined
    -0.14
    cla
    -0.14
    à¸ĩส
    -0.13
    lug
    -0.13
    วาà¸ĩ
    -0.13
    lest
    -0.13
    POSITIVE LOGITS
     allow
    0.93
     allows
    0.86
     allowing
    0.84
    allow
    0.83
     Allow
    0.79
    Allow
    0.76
     allowed
    0.71
    allows
    0.71
    åħģ
    0.71
     Allows
    0.69
    Activations Density 0.082%

    No Known Activations