© 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. 41860
    Prev
    Next
    INDEX
    Explanations

    phrases related to detailed or thorough descriptions

    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
    azon
    -0.16
    endor
    -0.14
     Anth
    -0.13
    é«ĺéĢŁ
    -0.13
    æıIJ
    -0.13
    ãģªãģĬ
    -0.13
    addir
    -0.13
    appl
    -0.13
    каÑģ
    -0.12
     swift
    -0.12
    POSITIVE LOGITS
     detailed
    0.40
     comprehensive
    0.37
     thorough
    0.34
    详
    0.33
     Detailed
    0.31
    Detailed
    0.30
     longer
    0.30
     length
    0.27
    -length
    0.27
     detail
    0.27
    Activations Density 0.095%

    No Known Activations