© 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. 86994
    Prev
    Next
    INDEX
    Explanations

    concepts related to rules and systems within competitive environments

    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
    alo
    -0.07
    onu
    -0.07
    ekk
    -0.06
     phong
    -0.06
    edu
    -0.06
    _DRIVE
    -0.06
    è¼Ŀ
    -0.06
    ÑģилÑĮ
    -0.06
    iversity
    -0.06
    _GENERIC
    -0.06
    POSITIVE LOGITS
     rules
    0.15
     Rules
    0.14
    rules
    0.13
    Rules
    0.12
     RULE
    0.10
     пÑĢавила
    0.10
    _rules
    0.10
    /rules
    0.10
    .rules
    0.10
     rule
    0.09
    Activations Density 0.017%

    No Known Activations