© 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. 22256
    Prev
    Next
    INDEX
    Explanations

    references to statistics and metrics related to performance and participation

    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
    #End
    -0.14
     gridColumn
    -0.13
    cctor
    -0.12
    ãģ«ãģĭ
    -0.12
    redient
    -0.12
    posables
    -0.12
    ÐĽÐĺ
    -0.12
    depart
    -0.12
    elerine
    -0.12
     heraus
    -0.11
    POSITIVE LOGITS
     from
    1.06
    from
    0.84
     FROM
    0.72
    	from
    0.69
     från
    0.69
     dari
    0.66
    à¸Īาà¸ģ
    0.65
     từ
    0.63
     From
    0.62
    _from
    0.61
    Activations Density 0.073%

    No Known Activations