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

    Neuronpedia

    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. 82329
    Prev
    Next
    INDEX
    Explanations

    topics related to market and industry dynamics

    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
    illac
    -0.08
    antz
    -0.08
    anto
    -0.07
    èĨ
    -0.07
    Ģ
    -0.07
    õi
    -0.07
    ronics
    -0.07
    zan
    -0.06
    imb
    -0.06
    aben
    -0.06
    POSITIVE LOGITS
     purposes
    0.07
    <decltype
    0.07
     perfil
    0.06
     especialmente
    0.06
     actionTypes
    0.06
     particular
    0.06
     profile
    0.06
     contexts
    0.06
     needs
    0.06
    ldr
    0.06
    Activations Density 0.039%

    No Known Activations