© 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. 84305
    Prev
    Next
    INDEX
    Explanations

    references to informational content and news coverage

    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
    beit
    -0.07
    asse
    -0.07
    opo
    -0.06
    ilk
    -0.06
    öl
    -0.06
    lich
    -0.06
    chez
    -0.06
    ope
    -0.06
    عÙĨÙĪاÙĨ
    -0.06
     McGr
    -0.06
    POSITIVE LOGITS
     press
    0.07
    /Resources
    0.06
     mee
    0.06
    raquo
    0.06
    egin
    0.06
    ksi
    0.06
    953
    0.06
    ÙģØ©
    0.06
     Neg
    0.06
     ApiController
    0.06
    Activations Density 0.012%

    No Known Activations