© 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. 29674
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex social constructs and their definitions

    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
    ogan
    -0.17
    odos
    -0.17
    ost
    -0.15
     specific
    -0.14
     jeg
    -0.13
    eon
    -0.13
    PLICIT
    -0.13
    ernes
    -0.13
    cob
    -0.13
    osit
    -0.13
    POSITIVE LOGITS
     reality
    0.34
     Reality
    0.26
     what
    0.25
    Reality
    0.21
     who
    0.21
     ourselves
    0.20
    what
    0.20
     themselves
    0.20
     how
    0.19
     things
    0.19
    Activations Density 0.112%

    No Known Activations