© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41300
    Prev
    Next
    INDEX
    Explanations

    topics related to climate negotiations and environmental issues

    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
    atte
    -0.17
     Microsystems
    -0.14
     Beacon
    -0.14
    aight
    -0.14
    ableViewController
    -0.14
    ®
    -0.14
    rain
    -0.14
     prec
    -0.14
    atto
    -0.14
    reate
    -0.14
    POSITIVE LOGITS
     Adapt
    0.22
     adaptation
    0.20
     finance
    0.19
    eza
    0.18
     Loss
    0.17
     Least
    0.17
    finance
    0.17
    adapt
    0.16
     vulnerability
    0.16
     Gender
    0.16
    Activations Density 0.023%

    No Known Activations