© 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. 14011
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching or seeking something

    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
    ÑĴ
    -0.15
     verst
    -0.14
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.14
    ìĭ¬
    -0.14
     discredit
    -0.13
    ~-
    -0.13
    à¹ģà¸ķ
    -0.13
    머ëĭĪ
    -0.12
     greatness
    -0.12
    DTV
    -0.12
    POSITIVE LOGITS
     adequate
    0.46
     suitable
    0.45
     sufficient
    0.45
     enough
    0.45
    ufficient
    0.38
     decent
    0.37
     Enough
    0.36
     Suitable
    0.36
     appropriate
    0.35
     proper
    0.35
    Activations Density 0.089%

    No Known Activations