© 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. 29056
    Prev
    Next
    INDEX
    Explanations

    concepts related to climate change and investment metrics

    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
     Territory
    -0.07
    Adult
    -0.07
    budget
    -0.07
    ãĥ¼ãĥIJ
    -0.07
    stakes
    -0.07
    ERP
    -0.07
     tph
    -0.07
    andr
    -0.07
    (fullfile
    -0.07
    POSITIVE LOGITS
     investing
    0.08
     Moral
    0.07
    glob
    0.07
     instruments
    0.07
    atsapp
    0.07
     risk
    0.07
     globally
    0.07
     global
    0.07
     investment
    0.07
    857
    0.07
    Activations Density 0.074%

    No Known Activations