© 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. 41825
    Prev
    Next
    INDEX
    Explanations

    numeric data and statistical information

    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
    .scalablytyped
    -0.16
    CCR
    -0.15
     Drone
    -0.14
    autiful
    -0.13
     tweeting
    -0.13
    arella
    -0.13
    307
    -0.13
     Obr
    -0.13
     blog
    -0.13
     Occupy
    -0.13
    POSITIVE LOGITS
    199
    0.87
    Û±Û¹Û¹
    0.56
    198
    0.44
    200
    0.36
     Clinton
    0.30
    Clinton
    0.24
    992
    0.24
     Millennium
    0.23
     nin
    0.23
    ï¼Īå¹³æĪIJ
    0.23
    Activations Density 0.078%

    No Known Activations