© 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. 63261
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal issues and commercial transactions

    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
     greatness
    -0.14
     Parenthood
    -0.14
    getc
    -0.14
    istra
    -0.14
    UsageId
    -0.14
     Excellence
    -0.13
    entially
    -0.13
    ëĶ°
    -0.13
     itself
    -0.13
    äº
    -0.13
    POSITIVE LOGITS
     habits
    0.21
     choices
    0.20
     skills
    0.19
     prospects
    0.18
     outcomes
    0.17
     experiences
    0.17
     qualities
    0.17
     instincts
    0.16
    صد
    0.16
     coverage
    0.16
    Activations Density 0.064%

    No Known Activations