© 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. 63176
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanisms and their implications in social contexts

    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
    GRES
    -0.16
    istrovstvÃŃ
    -0.16
    encia
    -0.16
    imson
    -0.15
    égor
    -0.14
    -ÑĤаки
    -0.14
    elman
    -0.14
    IFY
    -0.14
    lbrace
    -0.14
    .makeText
    -0.14
    POSITIVE LOGITS
    ic
    0.20
    anical
    0.20
    intosh
    0.20
    ically
    0.19
    hift
    0.18
    cheng
    0.16
    (s
    0.16
    anism
    0.15
     principal
    0.15
    zzo
    0.15
    Activations Density 0.010%

    No Known Activations