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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 78469
    Prev
    Next
    INDEX
    Explanations

    symbolic representations and concepts related to creation and the universe

    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
     Abstract
    -0.06
     Trou
    -0.06
    elize
    -0.06
     maintain
    -0.06
     lex
    -0.06
     Power
    -0.06
     resist
    -0.06
    имÑĥ
    -0.05
     vs
    -0.05
     odds
    -0.05
    POSITIVE LOGITS
    wat
    0.07
    _extent
    0.06
     Vas
    0.06
     Briggs
    0.06
    aso
    0.06
     IDD
    0.06
    uras
    0.06
     Gand
    0.06
     trump
    0.06
    ÑĢад
    0.06
    Activations Density 0.004%

    No Known Activations