© 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. 29959
    Prev
    Next
    INDEX
    Explanations

    interactions and relationships involving strong emotions or sentiments

    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
    ANNEL
    -0.18
    ideos
    -0.18
    ITERAL
    -0.17
    voie
    -0.16
    toi
    -0.16
    abeth
    -0.14
    ekil
    -0.14
    ONGO
    -0.14
    ildo
    -0.14
    สำà¹Ģร
    -0.14
    POSITIVE LOGITS
     been
    0.24
     not
    0.23
     ready
    0.19
     gone
    0.18
     okay
    0.18
     use
    0.17
     responsible
    0.17
     come
    0.17
     good
    0.17
     OK
    0.17
    Activations Density 0.011%

    No Known Activations