© 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. 29034
    Prev
    Next
    INDEX
    Explanations

    prepositions and transitional phrases indicating direction or intent

    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
     and
    -0.29
     vÃł
    -0.19
     и
    -0.17
    	and
    -0.17
    åıĬåħ¶
    -0.16
     without
    -0.16
    à¹ģละม
    -0.15
     or
    -0.15
     ÈĻi
    -0.15
    à¹ģละ
    -0.15
    POSITIVE LOGITS
    intel
    0.13
    rib
    0.13
    hei
    0.13
    toi
    0.12
    ANNOT
    0.12
    alo
    0.12
    ยะ
    0.12
    chin
    0.12
    âĢ¦the
    0.12
    ulu
    0.12
    Activations Density 0.001%

    No Known Activations