© 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. 54759
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize individual agency and action

    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
    eceÄŁini
    -0.14
    rant
    -0.14
    rove
    -0.13
    agar
    -0.13
    ÑģÑĤиÑĤ
    -0.13
    did
    -0.13
    à¹ĥà¸Ļà¸ģาร
    -0.13
    à¥ĩब
    -0.12
    ennen
    -0.12
    emer
    -0.12
    POSITIVE LOGITS
     can
    0.81
    can
    0.56
    åı¯ä»¥
    0.53
     could
    0.47
     Can
    0.47
    Can
    0.46
    .can
    0.45
    	can
    0.43
     CAN
    0.41
    _can
    0.40
    Activations Density 0.209%

    No Known Activations