© 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. 17-LLAMASCOPE-RES-131K
    11. 95527
    Prev
    Next
    INDEX
    Explanations

    financial metrics and terms related to stock 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
    RECT
    -0.07
    assa
    -0.07
    loff
    -0.07
     Äijạo
    -0.07
    isti
    -0.07
    589
    -0.07
    illow
    -0.07
    .cx
    -0.07
    vore
    -0.07
    pone
    -0.07
    POSITIVE LOGITS
     Dunn
    0.06
     ble
    0.06
     Dirk
    0.06
     OnTrigger
    0.05
     ley
    0.05
     Guid
    0.05
     glac
    0.05
     anth
    0.05
    1
    0.05
    stery
    0.05
    Activations Density 0.001%

    No Known Activations