© 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 EvalsExportsAPI 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. 29309
    Prev
    Next
    INDEX
    Explanations

    references to regions or countries related to consumer markets

    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
    ánh
    -0.06
    akin
    -0.06
    аÑĢÑĤ
    -0.06
    deniz
    -0.06
     Zimmerman
    -0.06
    uyên
    -0.06
    ChangeEvent
    -0.06
    _Source
    -0.06
    ãĥ«ãĥī
    -0.06
    achu
    -0.06
    POSITIVE LOGITS
     miscellaneous
    0.07
    úmeros
    0.07
     authDomain
    0.07
    misc
    0.06
    ECTOR
    0.06
    ableView
    0.06
    rais
    0.06
    ît
    0.06
    uze
    0.06
    dete
    0.06
    Activations Density 0.001%

    No Known Activations