© 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. 123835
    Prev
    Next
    INDEX
    Explanations

    terms related to financial transactions or market value

    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
    ETA
    -0.07
    ombo
    -0.07
    κι
    -0.07
    erner
    -0.06
    765
    -0.06
    vig
    -0.06
    пÑĢимеÑĢ
    -0.06
    Esc
    -0.06
    @js
    -0.06
    np
    -0.06
    POSITIVE LOGITS
    hausen
    0.06
    woord
    0.06
    /animate
    0.06
    \Unit
    0.06
    andler
    0.06
    رÙģت
    0.06
     strapon
    0.06
    reek
    0.06
    ruptcy
    0.06
     remin
    0.05
    Activations Density 0.000%

    No Known Activations