© 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 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. 130752
    Prev
    Next
    INDEX
    Explanations

    special characters and diacritical marks in text

    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
    oci
    -0.08
    anges
    -0.06
    335
    -0.06
    omb
    -0.06
    238
    -0.06
    num
    -0.06
    iego
    -0.06
    orem
    -0.06
    orch
    -0.06
    ago
    -0.06
    POSITIVE LOGITS
    اÙĨÙĩ
    0.09
    aub
    0.08
    ÄŁÃ¼
    0.08
    dür
    0.07
    ÑĪка
    0.07
    fte
    0.07
    Æł
    0.07
    icken
    0.07
     ngang
    0.07
    âĶģ
    0.07
    Activations Density 0.009%

    No Known Activations