Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 32752
    Prev
    Next
    INDEX
    Explanations

    references to locations and spatial characteristics

    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
    arl
    -0.15
    лÑıд
    -0.15
    antal
    -0.15
     stir
    -0.15
    abaj
    -0.14
    thon
    -0.14
    271
    -0.14
    apel
    -0.14
    à¸ļาย
    -0.14
    agn
    -0.14
    POSITIVE LOGITS
     area
    0.79
     areas
    0.64
    area
    0.62
     Area
    0.58
     área
    0.55
     AREA
    0.54
    Area
    0.53
    -area
    0.52
    _area
    0.52
    areas
    0.51
    Activations Density 0.081%

    No Known Activations