© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 10-LLAMASCOPE-RES-32K
    6. 21961
    Prev
    Next
    INDEX
    Explanations

    mentions of financial aid, scholarships, and their impact on education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Äħż
    -0.16
    798
    -0.16
    arry
    -0.16
    _modes
    -0.15
    leston
    -0.15
    ismic
    -0.15
    .scalablytyped
    -0.15
    PCP
    -0.14
    eting
    -0.14
    uckles
    -0.14
    POSITIVE LOGITS
    rz
    0.16
    ãĢħ
    0.14
    ήÏĤ
    0.14
     help
    0.14
     suite
    0.13
     Alf
    0.13
    compass
    0.13
    ãģĿ
    0.13
     crowds
    0.13
    ithe
    0.13
    Activations Density 0.357%

    No Known Activations