© 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. 29997
    Prev
    Next
    INDEX
    Explanations

    concepts related to change and transformation

    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
    rine
    -0.14
    vetica
    -0.14
    bsites
    -0.13
    serie
    -0.13
    zsche
    -0.13
     queryInterface
    -0.13
    ipeg
    -0.13
    riad
    -0.13
    ymoon
    -0.12
    ziel
    -0.12
    POSITIVE LOGITS
    âĢ¦.↵↵
    0.15
    !↵↵↵↵
    0.13
     “âĢ¦
    0.13
    ÑĢаÑĤи
    0.13
    ï¼Ĭ
    0.13
    _INITIALIZ
    0.13
    ãĢĢ↵
    0.13
    fieldname
    0.12
    #echo
    0.12
     Thick
    0.12
    Activations Density 0.000%

    No Known Activations