© 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. 26-LLAMASCOPE-RES-32K
    11. 6223
    Prev
    Next
    INDEX
    Explanations

    terms related to societal status and roles within a community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hof
    -0.15
    ysz
    -0.15
    IDL
    -0.14
    ervas
    -0.14
    ysi
    -0.14
    ìĭ¤
    -0.14
     Sz
    -0.13
    à¤Ĥय
    -0.13
    ysl
    -0.13
     Steele
    -0.13
    POSITIVE LOGITS
     society
    1.09
     Society
    0.95
    ociety
    0.80
     societies
    0.72
     sociedad
    0.70
     société
    0.66
     societal
    0.54
     Soci
    0.45
    社ä¼ļ
    0.44
     ÑģÑĥÑģпÑĸлÑĮ
    0.42
    Activations Density 0.189%

    No Known Activations