© 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. 9-LLAMASCOPE-RES-131K
    11. 95235
    Prev
    Next
    INDEX
    Explanations

    programming-related elements such as data types and method declarations

    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
    rint
    -0.07
    çĤ®
    -0.06
    hack
    -0.06
    etri
    -0.06
    ovel
    -0.06
    ãĤ
    -0.06
    عÙģ
    -0.06
     Gaz
    -0.06
    ë¨
    -0.06
    281
    -0.06
    POSITIVE LOGITS
    mouseleave
    0.07
     McCabe
    0.06
    _INLINE
    0.06
    IPAddress
    0.06
    irse
    0.06
    okino
    0.06
    ản
    0.06
    KHTML
    0.05
    auce
    0.05
    ÎIJ
    0.05
    Activations Density 0.037%

    No Known Activations