© 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. 15811
    Prev
    Next
    INDEX
    Explanations

    instances of personal reflections and assumptions about experiences or emotions

    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
    TestingModule
    -0.17
    lettes
    -0.16
    MDB
    -0.14
    atsby
    -0.13
    icia
    -0.13
    ubyte
    -0.13
    umont
    -0.13
    .Xaml
    -0.13
    Need
    -0.13
    ÑĨей
    -0.13
    POSITIVE LOGITS
     must
    1.19
    must
    1.06
     Must
    1.03
    Must
    0.97
     MUST
    0.87
    .must
    0.76
    .Must
    0.65
    å¿ħé¡»
    0.62
     mustard
    0.58
     phải
    0.55
    Activations Density 0.063%

    No Known Activations