© 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. 15-LLAMASCOPE-RES-131K
    11. 88392
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to stock performance and investment strategies

    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
    affer
    -0.07
    ãĥ³ãĥĩãĤ£
    -0.06
    angan
    -0.06
     Millet
    -0.06
    esser
    -0.06
     Charl
    -0.06
     Åŀah
    -0.06
    ÙģÙĩ
    -0.06
    agger
    -0.06
     اØ
    -0.06
    POSITIVE LOGITS
     growth
    0.07
    growth
    0.07
    omo
    0.06
     Growth
    0.06
    orious
    0.06
    StatusCode
    0.06
    legen
    0.06
     price
    0.06
     eventual
    0.06
    ycop
    0.06
    Activations Density 0.011%

    No Known Activations