© 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. 15748
    Prev
    Next
    INDEX
    Explanations

    statistical rankings and comparisons

    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
    vest
    -0.14
    zion
    -0.14
    ument
    -0.14
    ãĥĭãĥĥãĤ¯
    -0.13
    ABCDEFGHI
    -0.13
    ount
    -0.13
    allo
    -0.13
     part
    -0.13
    .isPlaying
    -0.13
    ABCDEFG
    -0.13
    POSITIVE LOGITS
     among
    0.29
     amongst
    0.27
    among
    0.24
     rank
    0.23
     Among
    0.22
     overall
    0.21
    Among
    0.21
     worldwide
    0.20
     ranked
    0.20
     position
    0.20
    Activations Density 0.081%

    No Known Activations