© 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. 29750
    Prev
    Next
    INDEX
    Explanations

    the use of collective pronouns, especially "we," indicating shared perspectives or 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
    ollapsed
    -0.16
    reature
    -0.15
    ãĥ¼ãĥģ
    -0.15
    .firebaseapp
    -0.14
     am
    -0.14
    ategor
    -0.14
    ãĤ¹ãĥĨãĤ£
    -0.14
    arkin
    -0.14
    ElapsedTime
    -0.14
    imonial
    -0.13
    POSITIVE LOGITS
    igh
    0.20
    ibo
    0.19
    ’re
    0.18
    ’ll
    0.17
    'll
    0.17
    're
    0.17
    hr
    0.17
     mere
    0.16
     Turnbull
    0.16
    ild
    0.16
    Activations Density 0.087%

    No Known Activations