© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 28-LLAMASCOPE-RES-32K
    11. 28521
    Prev
    Next
    INDEX
    Explanations

    elements related to specific botanical names and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruž
    -0.14
    TriState
    -0.14
    ATTERN
    -0.14
     wages
    -0.14
    agens
    -0.14
    edImage
    -0.14
    stva
    -0.14
    彩票
    -0.13
    ÑĸÑĢ
    -0.13
     Wage
    -0.13
    POSITIVE LOGITS
     wood
    1.14
     Wood
    1.07
    Wood
    1.05
    wood
    1.05
    æľ¨
    0.89
    WOOD
    0.89
     Woods
    0.81
     woods
    0.76
    woods
    0.76
     wooden
    0.73
    Activations Density 0.161%

    No Known Activations