© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 22949
    Prev
    Next
    INDEX
    Explanations

    references to applications and technology-related content

    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
    ãģªãģĮãĤī
    -0.15
    laz
    -0.14
    umu
    -0.14
    ̣
    -0.14
    ang
    -0.13
    ìłĢ
    -0.13
    ender
    -0.13
     sino
    -0.13
    tach
    -0.13
     sondern
    -0.13
    POSITIVE LOGITS
     _______,
    0.22
    ï¼Įå¹¶
    0.21
     And
    0.20
     [],
    0.19
    And
    0.19
     à¹ģละ
    0.18
     {},
    0.18
    ï¼Į並
    0.18
    %,
    0.18
    ,and
    0.17
    Activations Density 0.460%

    No Known Activations