© 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. 69491
    Prev
    Next
    INDEX
    Explanations

    specific financial or market data related to trading 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
     mini
    -0.06
    apest
    -0.06
    rego
    -0.06
    jing
    -0.06
     gust
    -0.06
    esc
    -0.06
    alk
    -0.06
     Mini
    -0.06
    дÑĥ
    -0.06
    unami
    -0.06
    POSITIVE LOGITS
    iode
    0.08
    Lit
    0.07
    (assert
    0.07
    ÏĦαι
    0.06
     Lit
    0.06
    NotAllowed
    0.06
    Choices
    0.06
     Hou
    0.06
    INET
    0.06
    Owned
    0.06
    Activations Density 0.003%

    No Known Activations