© 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. 54915
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "there" and related phrases indicating presence or location

    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
    .ua
    -0.17
    abei
    -0.16
    arra
    -0.15
    uien
    -0.15
    ç¸
    -0.14
    eson
    -0.14
    away
    -0.14
    Ùī
    -0.14
    ãĥªãĥ¼ãĤº
    -0.14
    rido
    -0.13
    POSITIVE LOGITS
     longer
    0.25
     Longer
    0.21
     ready
    0.20
    abouts
    0.17
     longest
    0.17
    wick
    0.16
    embro
    0.16
     somewhere
    0.15
     physically
    0.15
    .datatables
    0.15
    Activations Density 0.077%

    No Known Activations