© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to quantities or amounts

    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
    elper
    -0.07
    .backend
    -0.07
    寸
    -0.06
    важа
    -0.06
    Äħż
    -0.06
    ded
    -0.06
     ÙģاÙĦ
    -0.06
     pathname
    -0.06
    imson
    -0.06
     Micha
    -0.06
    POSITIVE LOGITS
     usual
    0.10
    allen
    0.07
     reality
    0.07
    usual
    0.07
    others
    0.07
     intended
    0.06
     what
    0.06
     necessary
    0.06
     normal
    0.06
    erge
    0.06
    Activations Density 0.018%

    No Known Activations