© 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. 72984
    Prev
    Next
    INDEX
    Explanations

    financial and quantitative data related to economic performance

    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
     Cout
    -0.06
    iel
    -0.06
     unchecked
    -0.06
    angent
    -0.06
    ARGER
    -0.06
    adge
    -0.06
     Attribution
    -0.06
    angu
    -0.05
    umin
    -0.05
     Honest
    -0.05
    POSITIVE LOGITS
    ikon
    0.07
    kla
    0.07
    WriteBarrier
    0.06
     Baxter
    0.06
    ึ
    0.06
    екаÑĢ
    0.06
    axter
    0.06
     OnTrigger
    0.06
    TreeWidgetItem
    0.06
    ëijĺ
    0.06
    Activations Density 0.001%

    No Known Activations