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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30521
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with a sports context or reporting

    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
     frat
    -0.15
    è³
    -0.14
    idget
    -0.14
    KeyEvent
    -0.14
    edException
    -0.14
    ön
    -0.14
    æļĹ
    -0.14
    urch
    -0.14
    acias
    -0.14
    retch
    -0.13
    POSITIVE LOGITS
    /tos
    0.18
    Studio
    0.16
     pre
    0.16
     Studio
    0.16
     studio
    0.16
    studio
    0.16
    670
    0.15
     McConnell
    0.15
    иÑĤом
    0.15
    preg
    0.15
    Activations Density 0.014%

    No Known Activations