Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54646
    Prev
    Next
    INDEX
    Explanations

    terms related to political power structures and governance

    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
    bone
    -0.16
    idious
    -0.16
    ially
    -0.15
    ovah
    -0.15
    ouro
    -0.14
    orarily
    -0.14
    ually
    -0.14
    IONS
    -0.14
    imates
    -0.14
    atically
    -0.14
    POSITIVE LOGITS
    ization
    0.98
    isation
    0.79
    åĮĸ
    0.75
    ification
    0.69
    IZATION
    0.63
    izations
    0.58
    izing
    0.56
     hóa
    0.56
    ización
    0.55
     åĮĸ
    0.55
    Activations Density 0.035%

    No Known Activations