© 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. 85697
    Prev
    Next
    INDEX
    Explanations

    concepts related to development, support, and improvement of systems or structures

    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
    irut
    -0.07
    nin
    -0.07
    รà¸ģ
    -0.07
    æľĽ
    -0.07
     _______,
    -0.07
    обÑĢаÐ
    -0.07
     mime
    -0.07
    à¸Ļà¸Ķ
    -0.06
    vier
    -0.06
    UTERS
    -0.06
    POSITIVE LOGITS
    ãģ«åIJij
    0.07
    åŀĭ
    0.06
     purposes
    0.06
     towards
    0.06
     toward
    0.06
     regarding
    0.06
    ise
    0.06
     for
    0.06
     aspect
    0.06
     exercises
    0.06
    Activations Density 0.033%

    No Known Activations