© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 104295
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous land and associated territories

    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
     ç±
    -0.06
    azel
    -0.06
     DIRECTORY
    -0.06
    adora
    -0.06
    MainThread
    -0.06
    ocos
    -0.06
     Barry
    -0.06
    ãĤ¹ãĥŀ
    -0.06
    odka
    -0.06
    usra
    -0.06
    POSITIVE LOGITS
    .sb
    0.06
    ARAM
    0.06
     privilege
    0.06
     kâ
    0.06
    AMIL
    0.06
    ÑĪев
    0.06
    raz
    0.06
     rentals
    0.06
    aval
    0.06
    غراÙģ
    0.06
    Activations Density 0.010%

    No Known Activations