© 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. 29037
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial performance and stock analysis

    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
    SPEC
    -0.07
    conde
    -0.07
    ä»ķ
    -0.07
     ç¤
    -0.07
    ÑģÑı
    -0.06
    åĭ
    -0.06
    Videos
    -0.06
     подав
    -0.06
    ikal
    -0.06
    NEL
    -0.06
    POSITIVE LOGITS
    ernet
    0.07
    opers
    0.06
     cach
    0.06
     needle
    0.06
     pq
    0.06
    erts
    0.06
     rev
    0.05
     habit
    0.05
     Ribbon
    0.05
    rn
    0.05
    Activations Density 0.002%

    No Known Activations