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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126444
    Prev
    Next
    INDEX
    Explanations

    mentions of cloud computing and related services

    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
     McCart
    -0.07
    à¹ģล
    -0.07
    Broad
    -0.07
    inya
    -0.07
     @}
    -0.07
     éģĵ
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    arking
    -0.07
    hled
    -0.06
    ubu
    -0.06
    POSITIVE LOGITS
     local
    0.11
     hosted
    0.09
    local
    0.09
     Local
    0.08
     home
    0.08
    /local
    0.07
     private
    0.07
     lokale
    0.07
     locally
    0.07
     server
    0.07
    Activations Density 0.016%

    No Known Activations