© 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. 33039
    Prev
    Next
    INDEX
    Explanations

    expressions of expectation or anticipation regarding actions and 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
    alah
    -0.16
    ÑģÑĮ
    -0.16
    esser
    -0.16
    iskey
    -0.15
    erton
    -0.15
    427
    -0.15
    ruh
    -0.15
    ÅĪ
    -0.14
    xCD
    -0.14
    èĿ
    -0.14
    POSITIVE LOGITS
     faint
    0.32
     losing
    0.22
     die
    0.22
     lose
    0.22
     breakdown
    0.21
     suff
    0.21
     DIE
    0.20
     collapse
    0.20
     ke
    0.20
     Suff
    0.19
    Activations Density 0.046%

    No Known Activations