© 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. 17-LLAMASCOPE-RES-131K
    11. 58140
    Prev
    Next
    INDEX
    Explanations

    references to governmental or organizational agendas and initiatives related to economic growth in Africa

    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
    ÑĢак
    -0.07
    cox
    -0.07
    rak
    -0.07
    вий
    -0.07
    gne
    -0.06
    веÑī
    -0.06
    ÑĢÑı
    -0.06
    ream
    -0.06
     buffered
    -0.06
    ué
    -0.06
    POSITIVE LOGITS
     commercials
    0.06
     Archer
    0.06
    ixin
    0.06
     Customer
    0.06
     bouquet
    0.06
    OnError
    0.05
     Kens
    0.05
    ç¢İ
    0.05
    едаг
    0.05
    pto
    0.05
    Activations Density 0.002%

    No Known Activations