© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29099
    Prev
    Next
    INDEX
    Explanations

    references to Buddhist concepts and mindfulness

    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
    age
    -0.16
    iner
    -0.16
    IFA
    -0.15
    ç®±
    -0.15
     hel
    -0.15
    еж
    -0.15
    ãĥ¼ãĤ¸
    -0.14
    inge
    -0.14
    artz
    -0.14
     Pierce
    -0.14
    POSITIVE LOGITS
     Maj
    0.19
    imli
    0.16
     Ther
    0.16
    ATIO
    0.15
    offee
    0.15
    andler
    0.15
    jsonwebtoken
    0.15
    lesc
    0.14
    ullan
    0.14
    åİŁå§ĭ
    0.14
    Activations Density 0.005%

    No Known Activations