© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 518
    Prev
    Next
    INDEX
    Explanations

    attributes and features of tablet devices in educational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iPhones
    -0.19
    iPhone
    -0.19
     iPhone
    -0.19
    iphone
    -0.19
     iphone
    -0.17
    rowned
    -0.17
    isque
    -0.17
     phones
    -0.16
     Phones
    -0.16
    Phones
    -0.16
    POSITIVE LOGITS
     tablet
    0.51
     tablets
    0.46
    tablet
    0.44
     Tablet
    0.43
     Tablets
    0.43
     Tab
    0.29
    ÑĤаб
    0.28
     ÑĤаблеÑĤ
    0.28
     slate
    0.27
     iPad
    0.26
    Activations Density 0.047%

    No Known Activations