© 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. 54756
    Prev
    Next
    INDEX
    Explanations

    the word "massive" in various contexts

    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
    bos
    -0.17
    bie
    -0.17
    ILLISE
    -0.17
    bies
    -0.16
    bis
    -0.15
    apos
    -0.15
    ing
    -0.15
    ÑĢеж
    -0.15
    ed
    -0.15
    isan
    -0.15
    POSITIVE LOGITS
     amounts
    0.40
     amount
    0.33
    amount
    0.32
     Amount
    0.31
    Amount
    0.26
    -scale
    0.24
     quantities
    0.23
     undertaking
    0.22
    .amount
    0.21
    Domains
    0.21
    Activations Density 0.051%

    No Known Activations