© 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. 86799
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial metrics and monitoring

    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
     inicial
    -0.08
    obile
    -0.07
    HEST
    -0.06
    side
    -0.06
     numberWith
    -0.06
    OOK
    -0.06
     stay
    -0.06
    amage
    -0.06
     Shack
    -0.06
    kowski
    -0.05
    POSITIVE LOGITS
     Ready
    0.09
     sooner
    0.08
     ready
    0.08
    READY
    0.08
     readiness
    0.08
    Ready
    0.08
    å±Ĩ
    0.07
    ready
    0.07
     nearing
    0.07
     Ø¢ÙħادÙĩ
    0.07
    Activations Density 0.126%

    No Known Activations