© 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. 54226
    Prev
    Next
    INDEX
    Explanations

    references to past events and legislative changes

    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
    ittest
    -0.19
    enden
    -0.15
    rgan
    -0.15
    -IN
    -0.15
    utow
    -0.14
    lz
    -0.14
    ounding
    -0.14
    tol
    -0.14
    ãĤ¸
    -0.14
    lán
    -0.14
    POSITIVE LOGITS
     in
    0.40
    InThe
    0.32
    à¹ĥà¸Ļ
    0.25
     future
    0.24
    à¹ĥà¸Ļà¸Ľ
    0.23
     åľ¨
    0.22
     previously
    0.22
    à¹īà¹ĥà¸Ļ
    0.20
     ÙģÙĬ
    0.20
    à¹Įà¹ĥà¸Ļ
    0.19
    Activations Density 0.064%

    No Known Activations