© 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 EvalsExportsinterp-engineNEWAPI 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. 39242
    Prev
    Next
    INDEX
    Explanations

    temporal references related to days of the week and specific dates

    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
    ازÙĩ
    -0.08
    emmel
    -0.07
    orr
    -0.07
    ialized
    -0.07
    ersist
    -0.07
    дÑı
    -0.07
     nieu
    -0.07
    çĶ
    -0.07
    frey
    -0.07
    afen
    -0.06
    POSITIVE LOGITS
    avid
    0.06
    IVED
    0.06
    iland
    0.05
    ×Ĺ
    0.05
     nam
    0.05
    atta
    0.05
    
    0.05
     thr
    0.05
    anco
    0.05
    etros
    0.05
    Activations Density 0.029%

    No Known Activations