© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15168
    Prev
    Next
    INDEX
    Explanations

    phrases related to designing and creating personal projects

    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
    á»ħ
    -0.17
    edo
    -0.17
    )prepare
    -0.15
    GLfloat
    -0.14
     |--------------------------------------------------------------------------↵
    -0.14
    acus
    -0.14
    IGIN
    -0.14
    lamaz
    -0.14
    aviest
    -0.14
     drv
    -0.14
    POSITIVE LOGITS
     ideal
    0.99
     perfect
    0.84
    ideal
    0.83
     Ideal
    0.82
    Ideal
    0.69
     Perfect
    0.67
    perfect
    0.67
    Perfect
    0.60
     PERF
    0.59
     dream
    0.47
    Activations Density 0.025%

    No Known Activations