© 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. 78053
    Prev
    Next
    INDEX
    Explanations

    technical indicators or codes related to server status and configurations

    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
    antor
    -0.07
    anch
    -0.07
     paddingBottom
    -0.06
    ocht
    -0.06
     fing
    -0.06
     ãĤ¢ãĥ«
    -0.06
    ury
    -0.06
    eteria
    -0.06
    еÑĢеÑĩ
    -0.06
     compreh
    -0.06
    POSITIVE LOGITS
    CAF
    0.07
    .binding
    0.06
    .DropDown
    0.06
    zimmer
    0.06
    ForResult
    0.06
    \Framework
    0.06
    388
    0.06
    idental
    0.06
    galement
    0.06
    аÑĤÑĭ
    0.06
    Activations Density 0.000%

    No Known Activations