© 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. 59361
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics related to business or economic performance

    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
    aimassage
    -0.06
    ehler
    -0.06
    kowski
    -0.06
    æ°Ĺ
    -0.06
    peech
    -0.06
    ufact
    -0.06
    constitution
    -0.06
    spir
    -0.06
    TestingModule
    -0.06
    curacy
    -0.06
    POSITIVE LOGITS
     objc
    0.07
    acle
    0.06
    ogn
    0.06
     !_
    0.06
    ibo
    0.06
    LAG
    0.06
    -č↵
    0.06
    CI
    0.06
    ãģıãĤĵ
    0.06
    trys
    0.05
    Activations Density 0.013%

    No Known Activations