© 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. 95099
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial expectations and returns

    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
    upply
    -0.07
    à¸Ńà¸ĩà¸Ħ
    -0.06
    imals
    -0.06
    erk
    -0.06
    acyj
    -0.06
    rix
    -0.06
    pricing
    -0.06
    _CTX
    -0.06
     Setter
    -0.06
    venes
    -0.06
    POSITIVE LOGITS
     prof
    0.09
     profit
    0.09
     Profit
    0.07
    ula
    0.07
     PROF
    0.07
    ULA
    0.07
     Closed
    0.06
    lose
    0.06
    Profit
    0.06
     Prof
    0.06
    Activations Density 0.016%

    No Known Activations