© 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 EvalsExportsAPI 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. 43182
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related phrases that express personal experiences

    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
    adele
    -0.16
    ãĥ³ãĤ¯
    -0.13
    íĥķ
    -0.12
    (DWORD
    -0.12
     attributeName
    -0.12
    ,arg
    -0.12
    sock
    -0.12
    uye
    -0.12
    èo
    -0.12
    _ISR
    -0.12
    POSITIVE LOGITS
    'll
    0.25
    've
    0.23
    ’ll
    0.23
    ’ve
    0.21
    'm
    0.21
    ’m
    0.20
     haven
    0.20
     wanted
    0.19
     plan
    0.17
     will
    0.17
    Activations Density 0.196%

    No Known Activations