© 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. 63581
    Prev
    Next
    INDEX
    Explanations

    negations or phrases indicating an absence or lack

    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
    "crypto
    -0.15
    importDefault
    -0.15
    ipeg
    -0.15
    Äįi
    -0.14
    ipa
    -0.14
    oug
    -0.14
    ousse
    -0.14
    ifestyles
    -0.13
    uely
    -0.13
    iek
    -0.13
    POSITIVE LOGITS
     anywhere
    1.23
     somewhere
    1.22
     elsewhere
    1.11
     nowhere
    1.09
     everywhere
    0.88
    Anywhere
    0.79
     wherever
    0.72
     Everywhere
    0.63
     Else
    0.62
    Else
    0.59
    Activations Density 0.039%

    No Known Activations