© 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. 87847
    Prev
    Next
    INDEX
    Explanations

    elements related to investment and financial market volatility

    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
     mixes
    -0.06
    udas
    -0.06
    roup
    -0.06
    ysi
    -0.06
    .dsl
    -0.06
     lens
    -0.06
    emme
    -0.06
    ocop
    -0.06
    ifik
    -0.06
    pring
    -0.06
    POSITIVE LOGITS
    akis
    0.07
     Ferr
    0.07
     movements
    0.06
     Pearson
    0.06
    162
    0.06
    ::-
    0.06
     trends
    0.06
     ebony
    0.06
    MC
    0.06
     market
    0.06
    Activations Density 0.007%

    No Known Activations