© 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. 17-LLAMASCOPE-RES-131K
    6. 17020
    Prev
    Next
    INDEX
    Explanations

    concepts related to social research methodologies and social inequality issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -cols
    -0.07
    upil
    -0.07
    ;element
    -0.07
     appel
    -0.07
    ấ
    -0.06
    ยà¸Ļ
    -0.06
    ActivityResult
    -0.06
    fon
    -0.06
    eer
    -0.06
     ÙĦÙĥÙĦ
    -0.06
    POSITIVE LOGITS
     topics
    0.07
     areas
    0.07
     themes
    0.07
    aland
    0.07
    any
    0.06
     Gund
    0.06
     Themes
    0.06
    OUR
    0.06
    (s
    0.06
    ington
    0.06
    Activations Density 0.016%

    No Known Activations