© 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. 3432
    Prev
    Next
    INDEX
    Explanations

    concepts related to organizational effectiveness and structure

    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
     åı¸
    -0.07
    andum
    -0.07
    .Override
    -0.07
    openh
    -0.06
    391
    -0.06
    à¸ģารà¹ĥà¸Ĭ
    -0.06
    rey
    -0.06
    963
    -0.06
    .metamodel
    -0.06
    åı¸
    -0.06
    POSITIVE LOGITS
     products
    0.09
     sales
    0.09
     Sales
    0.08
     Products
    0.08
     department
    0.08
     company
    0.08
     departments
    0.08
    /products
    0.08
     product
    0.08
     Bowman
    0.07
    Activations Density 0.024%

    No Known Activations