© 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. 22778
    Prev
    Next
    INDEX
    Explanations

    concepts related to sorting and evaluating truth amidst information overload

    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
    plural
    -0.14
    alth
    -0.14
    ulin
    -0.14
    ro
    -0.13
    ider
    -0.13
    roz
    -0.13
    irc
    -0.13
    YTE
    -0.13
     inexp
    -0.13
    .undefined
    -0.13
    POSITIVE LOGITS
     wheat
    0.34
     Wheat
    0.30
    signal
    0.22
     signal
    0.21
     genuine
    0.21
     separating
    0.21
     noise
    0.21
    noise
    0.21
     true
    0.20
     Noise
    0.20
    Activations Density 0.026%

    No Known Activations