© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107131
    Prev
    Next
    INDEX
    Explanations

    references to layers and functions in code

    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
    ÏĮδ
    -0.07
     plagiar
    -0.07
    ì§Ģëħ¸
    -0.07
    ï¼Īå¹³æĪIJ
    -0.07
    createCommand
    -0.07
    rio
    -0.07
    otten
    -0.07
    íķĺìļ°
    -0.07
    à¹Ĥรà¸ĩà¹ģรม
    -0.07
    ÑįÑĤ
    -0.07
    POSITIVE LOGITS
    .__
    0.07
    zelf
    0.07
     underlying
    0.06
    ivery
    0.06
     operating
    0.06
     isKindOfClass
    0.06
    /Dk
    0.06
     Juda
    0.06
     instanceof
    0.05
     =
    0.05
    Activations Density 0.029%

    No Known Activations