© 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. 15-LLAMASCOPE-RES-131K
    11. 90477
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values related to styling elements

    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
    anou
    -0.07
     gord
    -0.07
    ẫu
    -0.07
    edik
    -0.07
     nackte
    -0.07
     ä¸
    -0.06
     пой
    -0.06
    auc
    -0.06
    .generated
    -0.06
    DSA
    -0.06
    POSITIVE LOGITS
    igham
    0.07
     Sle
    0.06
    laps
    0.06
     Sheila
    0.06
    ãĥ©
    0.06
    alias
    0.05
    sat
    0.05
    еÑĤи
    0.05
    ANGE
    0.05
    UY
    0.05
    Activations Density 0.007%

    No Known Activations