© 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. 25130
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and relationships

    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
    lse
    -0.15
    aza
    -0.14
    ulp
    -0.14
    cxx
    -0.14
    obox
    -0.14
    cast
    -0.13
    ucu
    -0.13
     поÑĪ
    -0.13
     ADVISED
    -0.13
    aise
    -0.13
    POSITIVE LOGITS
     used
    0.92
     Used
    0.81
    used
    0.80
    Used
    0.76
     USED
    0.73
    -used
    0.65
    _used
    0.64
    USED
    0.62
    .used
    0.61
    çĶ¨äºİ
    0.57
    Activations Density 0.028%

    No Known Activations