Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63069
    Prev
    Next
    INDEX
    Explanations

    references to awards and prizes for freedom of expression

    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
    elli
    -0.14
    ether
    -0.14
    :↵↵↵↵
    -0.13
    "#
    -0.13
    Ñĩил
    -0.13
    .COLOR
    -0.13
     Scientist
    -0.13
    #{@
    -0.12
    irsch
    -0.12
     BCM
    -0.12
    POSITIVE LOGITS
    doch
    0.14
    umbnails
    0.14
     literal
    0.13
     figur
    0.13
    udeau
    0.13
    à¸Ĭ
    0.13
    uje
    0.13
    Gesture
    0.13
    itoris
    0.13
    andr
    0.12
    Activations Density 0.020%

    No Known Activations