© 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. 15-LLAMASCOPE-RES-131K
    11. 61598
    Prev
    Next
    INDEX
    Explanations

    connections between artists and their influences or works in societal contexts

    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
    üz
    -0.07
     Maison
    -0.07
    celik
    -0.07
    Å¡li
    -0.07
    zano
    -0.07
    erman
    -0.07
    üb
    -0.07
    ãģĻãģĻ
    -0.06
    sı
    -0.06
    yk
    -0.06
    POSITIVE LOGITS
    ábado
    0.07
    ayout
    0.07
    tel
    0.06
     only
    0.06
    exels
    0.06
    escription
    0.06
    à¸²à¸ł
    0.06
    ä¹ĭä¸Ģ
    0.06
    ãĤ¤ãĤº
    0.06
    itol
    0.06
    Activations Density 0.046%

    No Known Activations