© 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. 41871
    Prev
    Next
    INDEX
    Explanations

    instances of the word "taken" and its variations, particularly in the context of discussions or analyses of events

    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
     takes
    -0.20
     taking
    -0.19
     take
    -0.17
    thern
    -0.16
    taking
    -0.16
    takes
    -0.16
    ime
    -0.15
    taj
    -0.15
    raj
    -0.15
     takeaway
    -0.15
    POSITIVE LOGITS
     advantage
    0.31
    aways
    0.24
     care
    0.22
     advant
    0.21
     seriously
    0.20
    overs
    0.19
     refuge
    0.18
    uchi
    0.18
    umm
    0.17
    -home
    0.17
    Activations Density 0.033%

    No Known Activations