© 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. 9-LLAMASCOPE-RES-131K
    11. 98458
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to financial funds and investments

    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
    aphore
    -0.07
    lech
    -0.07
    Intialized
    -0.07
    riet
    -0.07
    chartInstance
    -0.07
    eyin
    -0.07
    bourne
    -0.06
    endcode
    -0.06
    лек
    -0.06
    баÑĩ
    -0.06
    POSITIVE LOGITS
    ird
    0.08
    ies
    0.07
     اÙĦسÙħ
    0.06
    º
    0.06
     eldre
    0.06
    opia
    0.06
     Duffy
    0.06
     à¹Ĩ
    0.06
    ê·ł
    0.06
    iam
    0.06
    Activations Density 0.385%

    No Known Activations