© 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. 41105
    Prev
    Next
    INDEX
    Explanations

    references to significant financial investments and urban development initiatives

    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
     Affero
    -0.15
    .cy
    -0.14
     sog
    -0.14
    indr
    -0.14
    CHK
    -0.14
     вÑģ
    -0.14
    orida
    -0.13
    resco
    -0.13
     Fog
    -0.13
    миниÑģÑĤÑĢа
    -0.13
    POSITIVE LOGITS
     LA
    0.43
     Los
    0.43
    Los
    0.39
    LA
    0.38
     UCLA
    0.37
     USC
    0.34
     LAP
    0.33
    .LA
    0.30
     los
    0.29
     Pasadena
    0.29
    Activations Density 0.122%

    No Known Activations