© 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. 44569
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" in various contexts

    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
     både
    -0.15
    ander
    -0.14
     sondern
    -0.14
     HOWEVER
    -0.14
     nữa
    -0.14
    دÙĩÙħ
    -0.14
    æĢĿãģĦ
    -0.14
     же
    -0.14
     esac
    -0.14
     lại
    -0.14
    POSITIVE LOGITS
    /or
    0.72
    /OR
    0.42
    rog
    0.30
    ä¸Ķ
    0.29
    rogen
    0.27
    /of
    0.26
    /o
    0.25
     hence
    0.25
    rew
    0.25
    наÑĩе
    0.24
    Activations Density 0.782%

    No Known Activations