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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 44565
    Prev
    Next
    INDEX
    Explanations

    punctuation and the presence of significant themes or claims in the text

    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
    à¸ĩหมà¸Ķ
    -0.16
    ?,?,?,?,
    -0.14
     огÑĢа
    -0.14
    ãİ
    -0.13
    lparr
    -0.13
    ghest
    -0.13
    ndon
    -0.12
     dahi
    -0.12
     seedu
    -0.12
     имÑĥ
    -0.12
    POSITIVE LOGITS
     both
    1.40
    both
    1.26
     Both
    1.20
    Both
    1.17
     BOTH
    1.14
    _both
    0.93
     beide
    0.92
     ambos
    0.87
     neither
    0.77
     obou
    0.77
    Activations Density 0.135%

    No Known Activations