© 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. 78451
    Prev
    Next
    INDEX
    Explanations

    mentions of "Wall Street."

    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
    ANNEL
    -0.09
    ushman
    -0.07
    VOKE
    -0.07
    klad
    -0.07
    ît
    -0.07
     ξεÏĦα
    -0.07
    oppel
    -0.07
    otal
    -0.07
    eness
    -0.07
    uchar
    -0.07
    POSITIVE LOGITS
    AB
    0.06
    aba
    0.06
     rag
    0.06
    abies
    0.06
     Sachs
    0.06
    /O
    0.06
    AFX
    0.05
    yt
    0.05
     sonic
    0.05
     Rag
    0.05
    Activations Density 0.001%

    No Known Activations