© 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. 54449
    Prev
    Next
    INDEX
    Explanations

    comparisons and relationships between entities

    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
    ξÏį
    -0.14
     nó
    -0.14
    ยà¸ĩ
    -0.14
    ikan
    -0.13
    å®ĥ
    -0.13
    arness
    -0.13
    }->
    -0.13
    ipel
    -0.13
    erk
    -0.13
    ettel
    -0.12
    POSITIVE LOGITS
     those
    1.28
    those
    1.12
     Those
    1.08
    Those
    1.03
    éĤ£äºĽ
    0.84
     ones
    0.79
     ceux
    0.72
     tÄĽch
    0.60
     Ones
    0.54
     denen
    0.53
    Activations Density 0.054%

    No Known Activations