© 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. 92430
    Prev
    Next
    INDEX
    Explanations

    terms related to economic analysis and structure

    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
    nel
    -0.07
    ä¸Ģ覧
    -0.07
    zell
    -0.07
    ÛĮÙĨÚ©
    -0.07
     malzem
    -0.07
    afort
    -0.07
    cek
    -0.07
    aliyet
    -0.06
    amel
    -0.06
    viol
    -0.06
    POSITIVE LOGITS
     equilibrium
    0.07
     Vick
    0.07
     under
    0.07
     Pare
    0.06
     Stack
    0.06
    erton
    0.06
    ÑĭÑĪ
    0.06
     optimal
    0.06
     always
    0.05
     Bang
    0.05
    Activations Density 0.001%

    No Known Activations