© 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. 33358
    Prev
    Next
    INDEX
    Explanations

    terms related to marine life and aquatic ecosystems

    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
    fg
    -0.15
    zia
    -0.14
    ÌĨ
    -0.14
    eko
    -0.14
    branches
    -0.14
    otime
    -0.14
    elah
    -0.13
    ÑĥÑĢи
    -0.13
    iol
    -0.13
    ListOf
    -0.13
    POSITIVE LOGITS
     populations
    0.37
     population
    0.33
    pop
    0.29
    population
    0.25
    -pop
    0.25
     pop
    0.23
     Population
    0.23
    _population
    0.21
     Pop
    0.21
    Population
    0.21
    Activations Density 0.069%

    No Known Activations