© 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. 89861
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation or special characters

    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
    ÅĻen
    -0.08
    еÑĦ
    -0.07
    аÑĢов
    -0.07
    mando
    -0.07
    :focus
    -0.07
    atcher
    -0.07
     ninh
    -0.07
     ÄĮer
    -0.07
    ady
    -0.07
    à¸ģร
    -0.07
    POSITIVE LOGITS
     unst
    0.06
     Other
    0.06
     FAST
    0.06
     CONNECT
    0.05
     blister
    0.05
     Everest
    0.05
     Slow
    0.05
     Fast
    0.05
     ↵↵
    0.05
     Clarkson
    0.05
    Activations Density 0.007%

    No Known Activations