© 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. 54706
    Prev
    Next
    INDEX
    Explanations

    references to specific tree species and their habitats

    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
     actionTypes
    -0.16
    vais
    -0.16
    ни
    -0.15
    ÙĪاء
    -0.15
    cie
    -0.15
    AGMA
    -0.15
    .simps
    -0.14
     Χα
    -0.14
    Īëĭ¤
    -0.14
    _BASIC
    -0.14
    POSITIVE LOGITS
     Melbourne
    0.46
     Victorian
    0.36
     Victoria
    0.31
     mel
    0.28
    Mel
    0.28
    Victoria
    0.26
     VIC
    0.26
     Mel
    0.24
     Bend
    0.24
     Caul
    0.24
    Activations Density 0.023%

    No Known Activations