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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106924
    Prev
    Next
    INDEX
    Explanations

    HTML elements and structure within a document

    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
    nger
    -0.08
    el
    -0.07
    евиÑĩ
    -0.07
    lander
    -0.07
     Infinity
    -0.07
    пÑĢи
    -0.07
    INGTON
    -0.06
    erli
    -0.06
    etz
    -0.06
    elik
    -0.06
    POSITIVE LOGITS
     nackte
    0.08
    ÑĢÑĥб
    0.06
    vnÃŃ
    0.06
     cryst
    0.06
     вÑĸк
    0.06
    à¸Ńà¹Ģร
    0.06
    quelle
    0.06
    hall
    0.06
    CR
    0.06
     CR
    0.05
    Activations Density 0.000%

    No Known Activations