© 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. 63739
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "over" related to intensity or degree

    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
    ugin
    -0.18
    ijken
    -0.17
    %%%%%%%%%%%%%%%%
    -0.16
    ract
    -0.16
    Äij
    -0.16
    izard
    -0.16
    ridge
    -0.16
    ometown
    -0.16
    rn
    -0.15
    rab
    -0.15
    POSITIVE LOGITS
    hetics
    0.20
    asis
    0.20
    rength
    0.18
    roph
    0.18
     gắng
    0.17
    ee
    0.17
    ellite
    0.17
    ria
    0.17
    udio
    0.17
    ream
    0.17
    Activations Density 0.050%

    No Known Activations