© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 4028
    Prev
    Next
    INDEX
    Explanations

    concepts related to investment risks and equity markets

    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
     discrepan
    -0.07
    _RG
    -0.07
    adata
    -0.07
    ÏĦαÏĤ
    -0.07
    KC
    -0.07
    imal
    -0.07
     valide
    -0.07
    ICLE
    -0.07
     indeb
    -0.07
    cke
    -0.07
    POSITIVE LOGITS
     risk
    0.15
     Risk
    0.13
     risks
    0.11
    Risk
    0.11
    risk
    0.11
     volatility
    0.10
    -risk
    0.10
     Ris
    0.10
    ãĥªãĤ¹
    0.09
     losses
    0.09
    Activations Density 0.026%

    No Known Activations