© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15668
    Prev
    Next
    INDEX
    Explanations

    elements related to box office numbers and movie performance statistics

    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
    .generated
    -0.16
    biên
    -0.14
    _Framework
    -0.14
    @js
    -0.14
    اÙĦØ©
    -0.14
     Decomp
    -0.14
    éro
    -0.14
    ugins
    -0.14
    моÑĤ
    -0.14
    eslint
    -0.14
    POSITIVE LOGITS
     Hunger
    0.26
     Avatar
    0.22
     Guardians
    0.21
     Mission
    0.21
    Transform
    0.21
     Transformers
    0.21
     Taken
    0.20
     Frozen
    0.20
     Rogue
    0.20
     Iron
    0.20
    Activations Density 0.075%

    No Known Activations