© 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 EvalsExportsinterp-engineNEWAPI 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. 86488
    Prev
    Next
    INDEX
    Explanations

    mentions of beverages and their effects on health and skin

    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
    etch
    -0.07
    745
    -0.07
    лл
    -0.06
    oui
    -0.06
     Haz
    -0.06
    azi
    -0.06
    ilver
    -0.06
    PropertyDescriptor
    -0.06
     DEC
    -0.06
    calar
    -0.06
    POSITIVE LOGITS
     Badge
    0.07
    ARA
    0.07
    IME
    0.07
    اگ
    0.06
    ufe
    0.06
     блÑİ
    0.06
    -inflammatory
    0.06
    лиÑĪком
    0.06
    ather
    0.06
    cker
    0.06
    Activations Density 0.008%

    No Known Activations