Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 82821
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistics related to foreign trade and economic performance

    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
    AT
    -0.07
     sounds
    -0.06
     "
    -0.06
     Gong
    -0.05
     people
    -0.05
    ạn
    -0.05
     Wort
    -0.05
     Sounds
    -0.05
    ura
    -0.05
     patch
    -0.05
    POSITIVE LOGITS
    Specifier
    0.08
    ãĥ¼ãĥł
    0.08
     imports
    0.07
    -trade
    0.07
    rzy
    0.07
     Imports
    0.07
     shipments
    0.07
    alytics
    0.07
    },'
    0.07
    ÑĥменÑĤ
    0.07
    Activations Density 0.001%

    No Known Activations