© 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. 9173
    Prev
    Next
    INDEX
    Explanations

    phrases and connectors related to sharing and cooperation

    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
     Rosenberg
    -0.19
     Pepper
    -0.15
     Ñįлем
    -0.15
    اÛĮاÙĨ
    -0.15
     amor
    -0.14
    ìĸ´ì§Ħ
    -0.14
    imizer
    -0.14
    è±
    -0.14
     DataService
    -0.13
    washer
    -0.13
    POSITIVE LOGITS
     receiving
    0.37
     reception
    0.36
     receive
    0.36
     receives
    0.32
     receiver
    0.32
     Reception
    0.31
     RECE
    0.31
    .receive
    0.31
     Receive
    0.31
     RECEIVE
    0.30
    Activations Density 0.008%

    No Known Activations