© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33319
    Prev
    Next
    INDEX
    Explanations

    phrases indicating timelines or sequences of events related to sports contracts and eligibility

    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
    olph
    -0.15
    á»ī
    -0.14
    arer
    -0.13
     Saul
    -0.13
    åĦĢ
    -0.13
     èĭ¥è¦ģ
    -0.13
    aghetti
    -0.13
    ughs
    -0.13
    POOL
    -0.13
    anova
    -0.12
    POSITIVE LOGITS
     season
    0.27
    201
    0.27
     Ñģез
    0.26
    aison
    0.24
     seasons
    0.23
    ason
    0.22
    season
    0.22
    202
    0.22
     temporada
    0.22
     Season
    0.22
    Activations Density 0.089%

    No Known Activations