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. 63104
    Prev
    Next
    INDEX
    Explanations

    references to regulatory details and their implications

    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
    ICODE
    -0.17
    ÏĨα
    -0.15
    hoff
    -0.14
    bara
    -0.14
    raison
    -0.14
     Sole
    -0.13
    edad
    -0.13
    utorial
    -0.13
    å¼¾
    -0.13
     Statements
    -0.13
    POSITIVE LOGITS
     details
    1.01
     Details
    0.85
    details
    0.82
     detail
    0.81
    Details
    0.77
    _details
    0.70
     DETAILS
    0.70
    -details
    0.70
    .details
    0.67
     detailed
    0.65
    Activations Density 0.031%

    No Known Activations