© 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. 42698
    Prev
    Next
    INDEX
    Explanations

    phrases related to blogging and audience engagement

    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
    utor
    -0.17
    dda
    -0.16
    _parms
    -0.15
    anela
    -0.14
    ostat
    -0.14
    usercontent
    -0.14
    orld
    -0.14
    ooled
    -0.14
    adoo
    -0.13
    él
    -0.13
    POSITIVE LOGITS
     know
    0.44
     knows
    0.40
     probably
    0.38
     likely
    0.33
     already
    0.33
     Know
    0.32
    know
    0.31
    çŁ¥éģĵ
    0.30
    probably
    0.30
     KNOW
    0.28
    Activations Density 0.042%

    No Known Activations