© 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. 117066
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions affecting organizations or events

    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
    ntl
    -0.08
    /Instruction
    -0.07
    /or
    -0.07
    kah
    -0.07
    nt
    -0.07
    殿
    -0.07
    vil
    -0.07
     елем
    -0.06
    .googleapis
    -0.06
     pokoj
    -0.06
    POSITIVE LOGITS
    ãģ°
    0.07
    bing
    0.07
    elper
    0.07
    à¹ģรà¸ģ
    0.06
    -up
    0.06
    -ÑĤаки
    0.06
    oned
    0.06
    ron
    0.06
    ilitating
    0.06
    ÑĥлÑĮ
    0.06
    Activations Density 0.050%

    No Known Activations