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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22541
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making and planning processes

    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
    ongyang
    -0.17
    ngrx
    -0.17
    .Magenta
    -0.15
    illard
    -0.14
    anzi
    -0.14
    ITTE
    -0.14
    utto
    -0.14
    emez
    -0.14
    abcdefghijklmnop
    -0.14
     vá»įng
    -0.13
    POSITIVE LOGITS
     decided
    0.80
     decide
    0.79
     decides
    0.70
     decision
    0.69
     deciding
    0.67
     Decide
    0.57
    åĨ³å®ļ
    0.56
     decid
    0.56
    dec
    0.52
     Decision
    0.52
    Activations Density 0.074%

    No Known Activations