© 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. 71229
    Prev
    Next
    INDEX
    Explanations

    numerical values related to financial data

    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
    ارÙĩ
    -0.07
    iesel
    -0.07
    avo
    -0.07
    .transition
    -0.07
    okud
    -0.07
    phia
    -0.07
    Ä°K
    -0.07
    ÐĽÐ¬
    -0.07
    è
    -0.06
    wik
    -0.06
    POSITIVE LOGITS
     ply
    0.07
    ứa
    0.06
     takson
    0.06
    oca
    0.05
    ê°Ħ
    0.05
     Sentinel
    0.05
    quential
    0.05
    >((
    0.05
     "()
    0.05
    WISE
    0.05
    Activations Density 0.000%

    No Known Activations