© 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. 10-LLAMASCOPE-RES-32K
    11. 21307
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating socioeconomic issues and health risks associated with specific conditions

    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
    anes
    -0.16
    ola
    -0.15
    ********************************************************
    -0.14
     weekends
    -0.14
    inda
    -0.14
    ient
    -0.14
    ome
    -0.14
    ung
    -0.13
    External
    -0.13
    .epam
    -0.13
    POSITIVE LOGITS
    èĢ³
    0.16
    ehir
    0.15
     Transmit
    0.15
    èij¡
    0.14
    zioni
    0.14
    ören
    0.14
    tü
    0.14
     pig
    0.14
    .preferences
    0.14
    رÙģ
    0.14
    Activations Density 0.379%

    No Known Activations