© 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. 29623
    Prev
    Next
    INDEX
    Explanations

    expressions of personal identity and subjective opinions

    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
     shouldBe
    -0.15
    shouldBe
    -0.15
     seemed
    -0.15
    ساÙĨ
    -0.14
    isay
    -0.14
    ovice
    -0.14
    Really
    -0.14
    .should
    -0.14
    ');?>"
    -0.14
    ttp
    -0.14
    POSITIVE LOGITS
    ä¸įä¼ļ
    0.27
     aren
    0.27
     will
    0.25
     won
    0.25
     don
    0.25
     isn
    0.25
     doesn
    0.24
     neither
    0.24
     não
    0.22
     WILL
    0.22
    Activations Density 0.283%

    No Known Activations