© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 54897
    Prev
    Next
    INDEX
    Explanations

    details related to garages and car storage

    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
    )(((
    -0.15
     Gros
    -0.14
    .ak
    -0.14
     MacOS
    -0.13
     Couch
    -0.13
    IME
    -0.13
     bát
    -0.13
    .matcher
    -0.13
    acers
    -0.13
    BarItem
    -0.13
    POSITIVE LOGITS
     garage
    0.57
     gar
    0.50
    gar
    0.46
     Garage
    0.45
    Gar
    0.41
     Gar
    0.39
     GAR
    0.37
     workshop
    0.35
     shed
    0.35
     barn
    0.31
    Activations Density 0.019%

    No Known Activations