© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    concepts related to foundational principles or starting points

    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
    agua
    -0.17
    ahoma
    -0.17
    471
    -0.17
    chner
    -0.16
    \CMS
    -0.16
     ëķ
    -0.16
    irting
    -0.15
    iglia
    -0.14
    ué
    -0.14
    itom
    -0.14
    POSITIVE LOGITS
     place
    0.68
     places
    0.56
    place
    0.55
     Place
    0.49
    Place
    0.47
     Places
    0.46
    places
    0.44
    -place
    0.44
     PLACE
    0.42
     lugar
    0.40
    Activations Density 0.017%

    No Known Activations